© 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. 13359
    Prev
    Next
    INDEX
    Explanations

    references to the word "lion" and related terms

    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
    52
    +0.15
    0.5%
    484
    +0.15
    0.5%
    306
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.10
    288
    +0.15
    0.11
    99
    +0.13
    0.07
    Negative Logits
    mble
    -1.31
     Seym
    -1.15
    lying
    -1.08
    ADRA
    -1.06
    chell
    -1.03
    Ñı
    -1.01
    galitarian
    -1.00
    irt
    -0.99
    skirts
    -0.97
    lishes
    -0.96
    POSITIVE LOGITS
    esses
    1.46
     lions
    1.32
    ous
    1.28
    eye
    1.24
    fish
    1.20
    ess
    1.14
    heart
    1.13
    hearted
    1.12
     Woods
    1.09
     lion
    1.07
    Activations Density 1.580%

    No Known Activations