© 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 EvalsExportsinterp-engineNEWAPI 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. 10714
    Prev
    Next
    INDEX
    Explanations

    incomplete words ending in 'in'

    oai_token-act-pair · gpt-3.5-turbo
    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
    563
    +0.14
    0.5%
    525
    +0.14
    0.5%
    67
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.07
    659
    +0.14
    0.07
    525
    +0.14
    0.06
    Negative Logits
     Seym
    -1.39
    hovah
    -1.20
     warr
    -1.11
     destro
    -1.07
    ¶æ
    -1.04
     compr
    -1.00
     behav
    -0.96
     confir
    -0.94
     trave
    -0.94
     challeng
    -0.93
    POSITIVE LOGITS
    strument
    2.11
    ned
    1.74
    ners
    1.70
    jury
    1.60
    clusive
    1.59
    cluded
    1.59
    ning
    1.55
    visible
    1.54
    iti
    1.51
    jured
    1.49
    Activations Density 2.256%

    No Known Activations