© 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. 10112
    Prev
    Next
    INDEX
    Explanations

    mentions of personal interactions and relationships

    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
    0.6%
    148
    +0.14
    0.5%
    714
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    647
    +0.17
    0.08
    665
    +0.14
    0.11
    206
    +0.12
    0.08
    Negative Logits
    ashtra
    -0.86
    akedown
    -0.85
    Adapter
    -0.81
    ivas
    -0.81
    orio
    -0.77
    hov
    -0.76
    atchewan
    -0.75
    orkshire
    -0.74
    tta
    -0.73
    dn
    -0.73
    POSITIVE LOGITS
    sole
    0.81
     previous
    0.78
    è¯
    0.76
     Treasure
    0.74
    ãĤ´ãĥ³
    0.73
    estone
    0.72
    shock
    0.72
    aceous
    0.70
    tu
    0.70
    ãĥĨãĤ£
    0.69
    Activations Density 2.246%

    No Known Activations