© 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 3072
    9. 8-RES_FS3072-JB
    11. 3057
    Prev
    Next
    INDEX
    Explanations

    dates and schedules

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    497
    +0.14
    0.6%
    640
    +0.13
    0.6%
    710
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.06
    421
    +0.13
    0.05
    52
    +0.11
    0.05
    Negative Logits
     Norn
    -0.81
    FUL
    -0.78
    REE
    -0.76
    IBLE
    -0.70
     Annotations
    -0.66
    ACTED
    -0.65
    lessly
    -0.64
    EMP
    -0.64
    IVE
    -0.64
    ATOR
    -0.64
    POSITIVE LOGITS
    stros
    1.25
    olith
    1.24
    itored
    1.23
    olithic
    1.18
    soon
    1.14
    etary
    1.12
    opoly
    1.10
    astery
    1.05
    ograph
    1.03
    ographs
    1.02
    Activations Density 0.693%

    No Known Activations