Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 6144
    5. 8-RES_FS6144-JB
    6. 5369
    Prev
    Next
    INDEX
    Explanations

    words related to politics and current events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    481
    +0.27
    1.3%
    447
    +0.15
    0.7%
    608
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.27
    0.14
    608
    +0.15
    0.13
    616
    +0.11
    0.09
    Negative Logits
    ometers
    -0.82
    heit
    -0.78
    esse
    -0.75
    tops
    -0.73
    IER
    -0.71
    orthy
    -0.69
    english
    -0.68
    itone
    -0.67
    Language
    -0.67
    anguage
    -0.67
    POSITIVE LOGITS
     debacle
    1.37
     fiasco
    1.30
     crackdown
    1.29
     controversy
    1.26
     revelations
    1.24
     crisis
    1.23
     upheaval
    1.23
     controversies
    1.23
     catastrophe
    1.23
     tragedy
    1.23
    Activations Density 1.857%

    No Known Activations