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. 809
    Prev
    Next
    INDEX
    Explanations

    financial transactions or business dealings

    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
    481
    +0.25
    1.3%
    373
    +0.23
    1.2%
    658
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.25
    0.06
    575
    +0.23
    0.09
    408
    +0.09
    0.10
    Negative Logits
    -)
    -0.82
    ?)
    -0.74
     ?)
    -0.73
    !]
    -0.69
    ?]
    -0.68
    ?).
    -0.67
    )?
    -0.67
    !)
    -0.66
    )</
    -0.66
    )!
    -0.66
    POSITIVE LOGITS
     disparate
    0.62
     respectively
    0.52
     interconnected
    0.51
     targeted
    0.50
     environments
    0.48
    ilaterally
    0.48
     diverse
    0.48
     nascent
    0.47
     various
    0.47
     southwestern
    0.46
    Activations Density 1.923%

    No Known Activations