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 49152
    5. 8-RES_FS49152-JB
    6. 26099
    Prev
    Next
    INDEX
    Explanations

    specific proper nouns related to technology and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    480
    +0.53
    2.9%
    266
    +0.13
    0.7%
    87
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.53
    0.02
    266
    +0.13
    0.07
    232
    +0.09
    0.07
    Negative Logits
     Aval
    -0.56
     AND
    -0.51
     and
    -0.45
     UNCLASSIFIED
    -0.44
     nomine
    -0.44
     Orwell
    -0.43
     indeed
    -0.43
     looph
    -0.42
     fault
    -0.41
    ãĤ°
    -0.41
    POSITIVE LOGITS
     alike
    0.91
     respectively
    0.77
     thereof
    0.70
     versa
    0.66
    oliath
    0.60
    cellaneous
    0.59
     thereto
    0.58
    rosso
    0.55
    sequent
    0.53
    depending
    0.53
    Activations Density 0.495%

    No Known Activations