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. 8131
    Prev
    Next
    INDEX
    Explanations

    references to petitions and requests for action from authorities

    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
    321
    +0.13
    0.6%
    300
    +0.12
    0.6%
    642
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.13
    0.05
    184
    +0.12
    0.03
    321
    +0.12
    0.04
    Negative Logits
    opsis
    -0.74
    ãĤ§
    -0.72
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.71
     spr
    -0.70
    ãĥ´ãĤ¡
    -0.70
     plunged
    -0.67
     Carbuncle
    -0.65
    ãĤ¡
    -0.64
    ãĥ¼ãĥĨãĤ£
    -0.64
     sidx
    -0.64
    POSITIVE LOGITS
     legislators
    0.94
     signatures
    0.92
     policymakers
    0.89
     FCC
    0.89
     governments
    0.86
     ratification
    0.84
     lawmakers
    0.84
     landlords
    0.83
     boycot
    0.81
     politicians
    0.80
    Activations Density 0.273%

    No Known Activations