© 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. 1532
    Prev
    Next
    INDEX
    Explanations

    statements discussing various topics

    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
    679
    +0.15
    0.5%
    540
    +0.14
    0.5%
    514
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.13
    154
    +0.14
    0.11
    514
    +0.14
    0.10
    Negative Logits
    izont
    -0.87
    è£ħ
    -0.86
    ãĤ¨ãĥ«
    -0.86
    çĶ°
    -0.86
    ãĥ¯ãĥ³
    -0.86
     welf
    -0.85
     salad
    -0.80
     ropes
    -0.80
     Mechdragon
    -0.79
     Rag
    -0.79
    POSITIVE LOGITS
    Ĵ
    1.16
    sure
    1.12
    certain
    1.10
    º
    1.10
    ¹
    1.09
    ates
    1.06
    âĢķ
    1.06
    ski
    1.03
    £
    1.02
    tains
    1.01
    Activations Density 0.632%

    No Known Activations