© 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. 1866
    Prev
    Next
    INDEX
    Explanations

    locations or 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
    311
    +0.17
    0.7%
    232
    +0.11
    0.5%
    671
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.11
    326
    +0.11
    0.08
    232
    +0.11
    0.07
    Negative Logits
    âķIJâķIJ
    -0.78
    eering
    -0.76
     unconscious
    -0.75
    enburg
    -0.75
    âĸ¬âĸ¬
    -0.75
     captivity
    -0.69
     Dayton
    -0.69
    ufact
    -0.67
    Lv
    -0.67
    Ĥİ
    -0.67
    POSITIVE LOGITS
    arez
    1.04
    ules
    0.88
    endish
    0.87
     Tob
    0.86
    ihara
    0.85
    ecause
    0.85
    idian
    0.82
    ule
    0.82
    peria
    0.82
    iao
    0.82
    Activations Density 1.050%

    No Known Activations