© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1487
    Prev
    Next
    INDEX
    Explanations

    names of countries

    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
    218
    +0.12
    0.5%
    206
    +0.12
    0.5%
    358
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.12
    0.02
    530
    +0.12
    0.02
    730
    +0.10
    0.02
    Negative Logits
    Tes
    -0.88
    assault
    -0.86
    anova
    -0.86
    cow
    -0.86
    anian
    -0.85
    tsy
    -0.85
    ele
    -0.83
    fam
    -0.83
    thood
    -0.83
    hend
    -0.82
    POSITIVE LOGITS
    ãĥIJ
    0.77
     Meteor
    0.75
     Ivory
    0.74
     Fenrir
    0.73
    åĬ
    0.71
     Valkyrie
    0.71
     LINK
    0.69
     Newfoundland
    0.69
     Shroud
    0.68
     Canberra
    0.65
    Activations Density 0.026%

    No Known Activations