© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10209
    Prev
    Next
    INDEX
    Explanations

    references to preparations or plans that are actively being made or thought out by individuals or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    433
    +0.15
    0.7%
    276
    +0.13
    0.6%
    385
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.04
    276
    +0.13
    0.03
    433
    +0.11
    0.03
    Negative Logits
    scape
    -0.89
    gie
    -0.87
    oran
    -0.82
    ez
    -0.77
    gest
    -0.76
    tan
    -0.74
    ternity
    -0.72
    Reviewer
    -0.72
    hare
    -0.72
    bing
    -0.72
    POSITIVE LOGITS
    iminary
    0.82
    hens
    0.79
    ENDED
    0.74
    essim
    0.72
    ublic
    0.71
    ocious
    0.71
    aneous
    0.71
    uberty
    0.70
    ension
    0.69
    aired
    0.69
    Activations Density 0.170%

    No Known Activations