© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6087
    Prev
    Next
    INDEX
    Explanations

    multi-syllable words with a high number of letters

    oai_token-act-pair · gpt-3.5-turbo

    words that contain the fragment "ig" with a preference towards the terminations of words

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    120
    +0.15
    0.5%
    702
    +0.15
    0.5%
    233
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.15
    0.06
    404
    +0.15
    0.06
    616
    +0.14
    0.06
    Negative Logits
     omission
    -0.85
     favor
    -0.85
    */(
    -0.85
     CPR
    -0.82
     CASE
    -0.81
     Falk
    -0.81
     Painter
    -0.80
     recommendations
    -0.80
     Vikings
    -0.79
     dossier
    -0.79
    POSITIVE LOGITS
    hai
    1.17
    ¬
    1.08
    lang
    1.02
    athom
    1.01
    asking
    0.99
    gian
    0.99
    imensional
    0.98
    arious
    0.97
    allic
    0.97
    umeric
    0.96
    Activations Density 0.859%

    No Known Activations