© 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. 3715
    Prev
    Next
    INDEX
    Explanations

    names and references to various individuals and entities

    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
    414
    +0.09
    0.5%
    427
    +0.08
    0.5%
    590
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.09
    0.05
    128
    +0.08
    0.05
    427
    +0.08
    0.04
    Negative Logits
     Puzzles
    -0.57
    BILITY
    -0.55
     Pieces
    -0.53
    OOL
    -0.53
    schild
    -0.53
     satell
    -0.52
    ILA
    -0.51
     mosqu
    -0.50
    ASY
    -0.49
    ILLE
    -0.49
    POSITIVE LOGITS
    -)
    1.05
    )[
    0.95
    ?)
    0.87
    )
    0.84
    >)
    0.83
    âĢ¦)
    0.81
    )(
    0.80
    ).[
    0.80
    )=
    0.78
    )."
    0.78
    Activations Density 0.438%

    No Known Activations