© 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. 2949
    Prev
    Next
    INDEX
    Explanations

    phrases indicating additional information or presenting new points

    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
    101
    +0.18
    0.6%
    679
    +0.16
    0.6%
    99
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.18
    0.07
    221
    +0.16
    0.05
    324
    +0.13
    0.04
    Negative Logits
    venge
    -0.91
     hearts
    -0.88
    girls
    -0.87
    crow
    -0.81
     Rumble
    -0.81
    kees
    -0.79
    balls
    -0.79
    liest
    -0.79
    fare
    -0.76
    icles
    -0.76
    POSITIVE LOGITS
    è£ħ
    1.05
     importantly
    0.97
    noon
    0.95
    gow
    0.90
    ional
    0.89
    entimes
    0.88
     insured
    0.87
    antly
    0.87
    ificantly
    0.87
     compl
    0.86
    Activations Density 0.468%

    No Known Activations