© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10138
    Prev
    Next
    INDEX
    Explanations

    contrasting statements

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.17
    0.7%
    608
    +0.11
    0.4%
    180
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.17
    0.20
    566
    +0.11
    0.15
    608
    +0.11
    0.21
    Negative Logits
    iph
    -0.78
     Bomb
    -0.73
     Banana
    -0.73
     raining
    -0.71
     Olymp
    -0.71
     Bang
    -0.69
    oz
    -0.68
     Basics
    -0.67
     sucks
    -0.67
     XY
    -0.67
    POSITIVE LOGITS
    etheless
    1.27
    ãĤ¦ãĤ¹
    1.02
     nonetheless
    1.01
     wondering
    0.93
     nevertheless
    0.90
     partName
    0.86
    ItemTracker
    0.85
    bably
    0.85
     implicitly
    0.84
     unwittingly
    0.84
    Activations Density 7.791%

    No Known Activations