© 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. 2848
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of locations

    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
    577
    +0.11
    0.5%
    673
    +0.10
    0.4%
    153
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.11
    0.06
    388
    +0.10
    0.07
    577
    +0.10
    0.07
    Negative Logits
    quickShipAvailable
    -0.83
    elight
    -0.71
     playable
    -0.69
    PDATE
    -0.69
     leve
    -0.65
    oiler
    -0.65
    STON
    -0.65
    onis
    -0.65
     spoiler
    -0.65
    ESCO
    -0.64
    POSITIVE LOGITS
    ans
    0.76
    users
    0.73
    atives
    0.73
     Tribe
    0.71
    ists
    0.70
     Sina
    0.69
    ikes
    0.68
     entails
    0.68
    ians
    0.67
    ai
    0.67
    Activations Density 2.544%

    No Known Activations