© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 25765
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    364
    +0.17
    0.8%
    686
    +0.12
    0.5%
    315
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    364
    +0.17
    0.03
    609
    +0.12
    0.02
    411
    +0.12
    0.02
    Negative Logits
    alties
    -0.73
     âĵĺ
    -0.67
     biodiversity
    -0.61
    uese
    -0.59
     installations
    -0.59
     havens
    -0.58
     tampering
    -0.58
     Leilan
    -0.58
    skirts
    -0.58
    xus
    -0.58
    POSITIVE LOGITS
    >:
    1.39
    >
    1.32
    ><
    1.32
    >)
    1.29
    >,
    1.23
    >(
    1.21
    >.
    1.16
    >"
    1.14
    ></
    1.14
    />
    1.06
    Activations Density 0.029%

    No Known Activations