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. 21864
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and specific technical details

    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
    119
    +0.10
    0.5%
    376
    +0.10
    0.5%
    384
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.10
    0.01
    583
    +0.10
    0.01
    728
    +0.10
    0.01
    Negative Logits
    rition
    -0.75
    pillar
    -0.74
    rity
    -0.73
    manship
    -0.69
    EMENT
    -0.68
    race
    -0.67
    ITAL
    -0.67
     Equality
    -0.65
    itated
    -0.65
    lished
    -0.64
    POSITIVE LOGITS
    veland
    1.17
    oser
    1.10
    aning
    1.08
    aves
    1.07
    vers
    1.01
    vel
    1.00
    zzle
    1.00
    fts
    0.99
    aned
    0.98
    fty
    0.98
    Activations Density 0.013%

    No Known Activations