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 24576
    5. 8-RES_FS24576-JB
    6. 647
    Prev
    Next
    INDEX
    Explanations

    references to political, governmental, and legislative topics

    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
    +0.25
    1.2%
    481
    +0.18
    0.8%
    477
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.25
    0.08
    477
    +0.18
    0.06
    177
    +0.12
    0.06
    Negative Logits
    fitting
    -0.70
    appropriate
    -0.68
    soType
    -0.61
    taining
    -0.60
    0200
    -0.59
    Fla
    -0.58
     Durham
    -0.57
    cellaneous
    -0.57
    ORY
    -0.56
    irming
    -0.56
    POSITIVE LOGITS
     lacks
    1.28
     cannot
    1.19
     possesses
    1.14
     lacked
    1.13
     behaves
    1.07
     tends
    1.07
     suffers
    1.04
     outper
    1.03
     relies
    1.03
     excel
    1.03
    Activations Density 0.501%

    No Known Activations