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. 11563
    Prev
    Next
    INDEX
    Explanations

    names of individuals involved in controversies or conflicts

    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
    +0.18
    0.9%
    134
    +0.14
    0.7%
    354
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.18
    0.07
    134
    +0.14
    0.05
    401
    +0.11
    0.06
    Negative Logits
    Tokens
    -0.70
     Leban
    -0.70
    eatures
    -0.70
    foundland
    -0.69
    cellaneous
    -0.68
    EngineDebug
    -0.66
    umption
    -0.63
    Anonymous
    -0.62
    olulu
    -0.61
    Marginal
    -0.61
    POSITIVE LOGITS
     violated
    1.10
     unfairly
    1.08
     stole
    1.06
     misled
    1.05
     cheated
    1.04
     should
    1.03
     interfered
    1.01
     owes
    1.00
     discriminated
    0.99
     mishand
    0.99
    Activations Density 0.340%

    No Known Activations