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. 11173
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person named Thompson

    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
    447
    +0.13
    0.6%
    420
    +0.09
    0.4%
    361
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.01
    650
    +0.09
    0.01
    525
    +0.09
    0.01
    Negative Logits
    utive
    -0.91
    mble
    -0.88
    atories
    -0.82
    rator
    -0.82
    rators
    -0.79
    eas
    -0.76
    mate
    -0.73
    ultan
    -0.71
    tes
    -0.70
    spring
    -0.70
    POSITIVE LOGITS
     Reuters
    0.82
     Browne
    0.81
    sonian
    0.78
     Gunn
    0.76
    stown
    0.73
    itton
    0.67
     Yor
    0.65
     Ammo
    0.64
    urai
    0.59
    acks
    0.59
    Activations Density 0.021%

    No Known Activations