© 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. 22
    Prev
    Next
    INDEX
    Explanations

    expressions related to exclamations and casual speech

    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
    393
    +0.17
    0.6%
    296
    +0.12
    0.4%
    105
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.17
    0.07
    607
    +0.12
    0.06
    427
    +0.11
    0.06
    Negative Logits
     fullest
    -0.78
    ensed
    -0.76
    iffe
    -0.76
     Grimm
    -0.76
     CPS
    -0.72
    Ranked
    -0.72
     cannabin
    -0.71
    ipel
    -0.68
    ivil
    -0.68
     Brune
    -0.67
    POSITIVE LOGITS
    wait
    1.10
     hey
    1.08
    $$$$
    0.97
     bye
    0.94
     wow
    0.93
    awk
    0.93
    Eh
    0.92
    Wait
    0.88
    Hey
    0.88
    Oh
    0.88
    Activations Density 2.123%

    No Known Activations