© 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 24576
    9. 8-RES_FS24576-JB
    11. 19774
    Prev
    Next
    INDEX
    Explanations

    names of people related to education or sports

    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
    651
    +0.12
    0.6%
    311
    +0.11
    0.5%
    554
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.02
    651
    +0.11
    0.02
    90
    +0.11
    0.02
    Negative Logits
    daq
    -0.70
    ntax
    -0.68
    Story
    -0.67
    CLOSE
    -0.66
    AW
    -0.65
     bait
    -0.64
    TOR
    -0.64
    ————————
    -0.60
    pher
    -0.59
    ãĥ£
    -0.59
    POSITIVE LOGITS
    ificate
    1.02
    itude
    0.98
    urbed
    0.97
    ogether
    0.94
    ainer
    0.91
    rait
    0.91
    aining
    0.91
    ained
    0.91
    ruck
    0.90
    iary
    0.89
    Activations Density 0.028%

    No Known Activations