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. 26065
    Prev
    Next
    INDEX
    Explanations

    references to the name "Justin" or "Bieber."

    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
    1
    +0.11
    0.5%
    161
    +0.10
    0.5%
    715
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1
    +0.11
    0.02
    161
    +0.10
    0.01
    261
    +0.09
    0.01
    Negative Logits
    ktop
    -0.76
    wark
    -0.74
     extremes
    -0.70
     mileage
    -0.69
    rums
    -0.66
    exempt
    -0.66
     confinement
    -0.66
    ansas
    -0.64
     womb
    -0.63
    unda
    -0.63
    POSITIVE LOGITS
     Bieber
    1.38
     Timber
    1.18
     Trudeau
    1.02
     Vernon
    0.91
     Upton
    0.90
     Wong
    0.85
     Hayward
    0.84
     Bour
    0.84
    Justin
    0.83
    onymous
    0.82
    Activations Density 0.006%

    No Known Activations