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. 392
    Prev
    Next
    INDEX
    Explanations

    content related to online platforms and community discussions

    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
    191
    +0.12
    0.6%
    356
    +0.10
    0.5%
    533
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    191
    +0.12
    0.04
    720
    +0.10
    0.05
    765
    +0.10
    0.05
    Negative Logits
    enance
    -0.67
    heartedly
    -0.64
    hered
    -0.60
    isin
    -0.60
    owered
    -0.60
    ãĤ´ãĥ³
    -0.59
    agen
    -0.59
    wash
    -0.58
    ida
    -0.58
    unes
    -0.58
    POSITIVE LOGITS
     ranging
    0.85
     besides
    0.82
     Including
    0.79
     none
    0.75
     plenty
    0.71
     namely
    0.70
     somet
    0.70
     including
    0.69
     lots
    0.69
    ruciating
    0.68
    Activations Density 0.438%

    No Known Activations