© 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 Local
    9. 6-RES_SCL-AJT
    11. 4092
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and related jargon

    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
    370
    +0.08
    0.6%
    155
    +0.06
    0.5%
    749
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.08
    -0.02
    675
    +0.06
    0.15
    308
    +0.06
    0.11
    Negative Logits
    zsche
    -0.54
    matic
    -0.51
    arios
    -0.49
    oscope
    -0.48
    urtle
    -0.46
    annel
    -0.46
    cius
    -0.45
     melan
    -0.44
    ofi
    -0.44
    ongyang
    -0.43
    POSITIVE LOGITS
     âĶľâĶĢâĶĢ
    0.61
     Appears
    0.60
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.57
    âĹ¼
    0.54
    PET
    0.53
    ãĥĺãĥ©
    0.52
    ãĥŁ
    0.50
    ··
    0.49
    ãĥ¼ãĥ³
    0.49
    ãĥ¬
    0.48
    Activations Density 7.723%

    No Known Activations