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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11749
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to space exploration

    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
    +0.50
    2.6%
    7
    +0.12
    0.6%
    266
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.50
    0.01
    7
    +0.12
    0.06
    266
    +0.10
    0.09
    Negative Logits
    ogether
    -0.61
    %:
    -0.60
     âĵĺ
    -0.59
    jer
    -0.59
    ilet
    -0.59
    isode
    -0.56
     Shirley
    -0.55
     Join
    -0.53
    rection
    -0.53
    ramid
    -0.53
    POSITIVE LOGITS
     already
    0.82
     notoriously
    0.74
     inexper
    0.67
     cumbers
    0.67
     constraints
    0.67
     technically
    0.64
     obviously
    0.63
     alot
    0.63
     deadlines
    0.63
     busy
    0.62
    Activations Density 1.139%

    No Known Activations