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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1231
    Prev
    Next
    INDEX
    Explanations

    cards and game rules related to a specific game involving creatures and tokens being placed on the battlefield

    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
    183
    +0.03
    0.5%
    43
    +0.03
    0.4%
    481
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    340
    +0.03
    0.01
    437
    +0.03
    0.01
    189
    +0.03
    0.01
    Negative Logits
    amy
    -0.20
    idy
    -0.19
    TY
    -0.19
    TR
    -0.18
    rings
    -0.18
     Survivor
    -0.17
    amina
    -0.17
    din
    -0.17
    imus
    -0.17
    RESULTS
    -0.16
    POSITIVE LOGITS
    ":"/
    0.25
    rouse
    0.24
    æ©
    0.22
    ntil
    0.21
    odium
    0.21
    ¿½
    0.21
    ":"","
    0.21
     oun
    0.21
     Franç
    0.20
    save
    0.20
    Activations Density 0.046%

    No Known Activations