© 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. 10149
    Prev
    Next
    INDEX
    Explanations

    instructions related to newsletter subscriptions and opt-out options

    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
    728
    +0.11
    0.5%
    184
    +0.09
    0.4%
    625
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    717
    +0.11
    0.01
    411
    +0.09
    0.01
    184
    +0.09
    0.01
    Negative Logits
    bugs
    -0.77
     Lau
    -0.74
     Situation
    -0.69
    rums
    -0.67
    oodle
    -0.64
     fronts
    -0.64
     Walls
    -0.62
    pher
    -0.60
     mole
    -0.60
    enegger
    -0.60
    POSITIVE LOGITS
     subscribing
    0.87
     parole
    0.71
     consent
    0.70
    aye
    0.70
    untarily
    0.69
     bec
    0.68
     gladly
    0.67
    ceive
    0.66
    animous
    0.65
    izabeth
    0.65
    Activations Density 0.055%

    No Known Activations