© 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. 40441
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions

    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
    23
    +0.08
    0.6%
    271
    +0.07
    0.6%
    447
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    442
    +0.08
    0.10
    316
    +0.07
    0.11
    514
    +0.07
    0.07
    Negative Logits
     Genie
    -0.43
    CLOSE
    -0.41
    ADRA
    -0.38
    atis
    -0.38
     illum
    -0.38
     Mehran
    -0.37
     Dee
    -0.36
    ãĤ´ãĥ³
    -0.36
     Forth
    -0.36
     arous
    -0.36
    POSITIVE LOGITS
    sburg
    0.60
    s
    0.60
    ingly
    0.58
    ered
    0.56
    er
    0.56
    ers
    0.53
    ering
    0.52
    erent
    0.52
    ership
    0.52
    erer
    0.51
    Activations Density 14.768%

    No Known Activations