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. 327
    Prev
    Next
    INDEX
    Explanations

    locations or places.

    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
    683
    +0.14
    0.6%
    373
    +0.13
    0.6%
    481
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.14
    0.04
    659
    +0.13
    0.04
    354
    +0.13
    0.04
    Negative Logits
    ashtra
    -0.63
    itely
    -0.60
    raught
    -0.60
    ranged
    -0.59
    noon
    -0.57
     polar
    -0.56
    assment
    -0.54
    stellar
    -0.54
    istor
    -0.54
     transient
    -0.53
    POSITIVE LOGITS
    uese
    1.02
    zona
    0.74
    anski
    0.71
    otto
    0.70
    ogl
    0.70
     guiActiveUnfocused
    0.70
     Blanc
    0.69
     Daniels
    0.68
    anche
    0.65
     Mania
    0.65
    Activations Density 0.187%

    No Known Activations