© 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. 9783
    Prev
    Next
    INDEX
    Explanations

    financial and economic-related terms and details

    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
    420
    +0.13
    0.6%
    97
    +0.11
    0.5%
    649
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.03
    579
    +0.11
    0.03
    326
    +0.10
    0.02
    Negative Logits
    aceutical
    -0.71
    ourced
    -0.66
    ourcing
    -0.61
    izon
    -0.60
    naires
    -0.60
    ohydrate
    -0.58
    iversal
    -0.57
    aciously
    -0.56
    anamo
    -0.56
    uitous
    -0.56
    POSITIVE LOGITS
    llers
    1.30
    ller
    1.26
    vich
    1.21
    ptic
    1.14
    ls
    1.12
    letal
    1.10
    lling
    1.07
    rer
    1.05
    rers
    1.03
    rette
    1.02
    Activations Density 0.076%

    No Known Activations