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. 26122
    Prev
    Next
    INDEX
    Explanations

    terms related to influence and influential individuals

    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
    12
    +0.09
    0.4%
    67
    +0.09
    0.4%
    549
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.09
    0.01
    536
    +0.09
    0.01
    647
    +0.09
    0.01
    Negative Logits
     pardon
    -0.70
     McDonnell
    -0.69
    iffs
    -0.65
     Peninsula
    -0.65
    dress
    -0.63
     Revision
    -0.63
     Fist
    -0.63
     Barrett
    -0.63
     Pwr
    -0.62
     Ancients
    -0.62
    POSITIVE LOGITS
    encers
    1.61
    encer
    1.59
    encing
    1.24
     influ
    1.14
    enced
    1.14
    ences
    1.13
    enza
    0.98
    ential
    0.97
    cci
    0.91
    enz
    0.91
    Activations Density 0.003%

    No Known Activations