© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 548
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions, analysis, and events involving the police and legal aspects

    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
    699
    +0.14
    0.7%
    218
    +0.10
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.14
    0.11
    102
    +0.10
    0.11
    566
    +0.10
    0.09
    Negative Logits
    currently
    -0.78
     presently
    -0.70
    uras
    -0.66
    today
    -0.65
     currently
    -0.65
     Current
    -0.64
    allows
    -0.64
    rouse
    -0.64
    uchi
    -0.64
    projects
    -0.64
    POSITIVE LOGITS
    hes
    1.08
     instrumental
    1.00
     mistaken
    0.98
     intentional
    0.97
     originally
    0.93
     unintentional
    0.93
     negligent
    0.91
     unsuccessful
    0.91
     careless
    0.90
    wolves
    0.89
    Activations Density 0.525%

    No Known Activations