© 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 Local
    9. 6-RES_SCL-AJT
    11. 33959
    Prev
    Next
    INDEX
    Explanations

    specific game terminology related to updates, moves, and strategies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    447
    +0.18
    0.8%
    575
    +0.14
    0.6%
    97
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    97
    +0.18
    0.08
    570
    +0.14
    0.02
    78
    +0.13
    0.06
    Negative Logits
    aylor
    -0.79
    vale
    -0.78
    inges
    -0.76
    ingen
    -0.74
    agar
    -0.74
    algia
    -0.72
    ysis
    -0.72
    çļ
    -0.70
    omial
    -0.69
     Reborn
    -0.69
    POSITIVE LOGITS
    peed
    1.00
    ets
    0.98
    ments
    0.97
    able
    0.93
    pool
    0.89
    brates
    0.84
    ives
    0.82
    overs
    0.81
    move
    0.79
    wright
    0.79
    Activations Density 7.613%

    No Known Activations