Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 11170
    Prev
    Next
    INDEX
    Explanations

    text related to government projects and initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    480
    +0.47
    2.4%
    641
    +0.10
    0.5%
    86
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.47
    0.00
    641
    +0.10
    0.07
    86
    +0.10
    0.05
    Negative Logits
    toggle
    -0.71
    umably
    -0.70
    edit
    -0.67
    ?),
    -0.66
    oof
    -0.61
    lua
    -0.61
    Ĭ±
    -0.60
     Oops
    -0.60
     Presumably
    -0.59
    surprisingly
    -0.59
    POSITIVE LOGITS
     responsibly
    0.96
     our
    0.75
     courageous
    0.75
     lawful
    0.71
     dignity
    0.70
    .","
    0.69
     grassroots
    0.69
     compassionate
    0.69
     respectfully
    0.69
     endeavors
    0.68
    Activations Density 1.027%

    No Known Activations