© 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. 34700
    Prev
    Next
    INDEX
    Explanations

    measurement units and numerical values related to physical dimensions

    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
    641
    +0.16
    0.6%
    483
    +0.12
    0.5%
    442
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.16
    0.20
    434
    +0.12
    0.06
    2
    +0.12
    0.01
    Negative Logits
    abase
    -0.78
     Ridley
    -0.70
    ADRA
    -0.68
     Foss
    -0.68
     Masquerade
    -0.68
     Leia
    -0.66
     guiName
    -0.65
     filib
    -0.63
    iru
    -0.63
     trace
    -0.63
    POSITIVE LOGITS
    acan
    0.83
    999
    0.81
    士
    0.81
    9999
    0.73
    090
    0.73
     nails
    0.72
    autions
    0.70
    295
    0.69
    dogs
    0.68
    clock
    0.68
    Activations Density 14.338%

    No Known Activations