© 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. 3992
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical expressions like numerical digits, mathematical operators, and software commands

    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
    447
    +0.23
    1.0%
    237
    +0.12
    0.5%
    23
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.23
    0.06
    167
    +0.12
    -0.15
    736
    +0.12
    0.11
    Negative Logits
    adesh
    -0.73
    naissance
    -0.66
    aminer
    -0.66
     Cruel
    -0.65
    heit
    -0.64
     Berks
    -0.64
     gull
    -0.64
    romeda
    -0.62
     harbor
    -0.61
     spoiler
    -0.60
    POSITIVE LOGITS
    ================================================================
    0.74
    oglu
    0.72
    TEXTURE
    0.70
     Anarchy
    0.68
    --------------------
    0.65
     UCH
    0.60
     availability
    0.60
    052
    0.59
    -----------
    0.59
    κ
    0.58
    Activations Density 37.264%

    No Known Activations