© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 9729
    Prev
    Next
    INDEX
    Explanations

    information related to political events, investigative journalism, and potential security threats

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    679
    +0.14
    0.7%
    440
    +0.12
    0.6%
    640
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.14
    440
    +0.12
    0.12
    430
    +0.12
    0.13
    Negative Logits
     fishes
    -0.74
     volunte
    -0.73
     minion
    -0.70
    unts
    -0.69
     affili
    -0.69
     zone
    -0.68
    natureconservancy
    -0.67
    ŃĶ
    -0.67
     regenerate
    -0.66
     cellar
    -0.66
    POSITIVE LOGITS
     Similarly
    1.41
     Later
    1.36
     Shortly
    1.29
     Afterwards
    1.28
     Meanwhile
    1.26
     Likewise
    1.24
     Ironically
    1.22
     Eventually
    1.21
     Another
    1.18
     Soon
    1.17
    Activations Density 0.670%

    No Known Activations