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. 23570
    Prev
    Next
    INDEX
    Explanations

    references to political groups and social issues

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.15
    0.7%
    481
    +0.09
    0.4%
    126
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    714
    +0.15
    0.04
    575
    +0.09
    0.05
    51
    +0.09
    0.04
    Negative Logits
    ãĤ´ãĥ³
    -0.69
    OWS
    -0.68
    Ĥİ
    -0.64
    ķ
    -0.63
    inventoryQuantity
    -0.63
     IMAGES
    -0.60
    Ł
    -0.60
    ãĥĥ
    -0.59
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.59
    ĵ
    -0.58
    POSITIVE LOGITS
     lurking
    1.00
     waiting
    0.91
     devoted
    0.90
     available
    0.86
     vying
    0.85
     involved
    0.84
     roaming
    0.83
     dedicated
    0.82
     lined
    0.81
     circulating
    0.80
    Activations Density 0.245%

    No Known Activations