© 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. 9382
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns ('its', 'my', 'his', 'our', 'your', etc.)

    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
    362
    +0.14
    0.7%
    481
    +0.11
    0.5%
    92
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.09
    608
    +0.11
    0.07
    393
    +0.10
    0.07
    Negative Logits
    igate
    -0.90
    adata
    -0.78
    lehem
    -0.75
    emonium
    -0.75
    ropolitan
    -0.75
    AAAA
    -0.74
    onym
    -0.73
    etsk
    -0.73
    cum
    -0.72
    illac
    -0.69
    POSITIVE LOGITS
     dealings
    1.16
     handling
    1.04
     demeanor
    0.99
     surroundings
    0.99
     portrayal
    0.94
     upbringing
    0.94
     approach
    0.92
     environment
    0.91
     situation
    0.90
     behavior
    0.85
    Activations Density 0.375%

    No Known Activations