Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 1149
    Prev
    Next
    INDEX
    Explanations

    information related to sports seasons, particularly highlighting regular season statistics and events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    710
    +0.16
    0.7%
    260
    +0.10
    0.4%
    718
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.16
    0.03
    260
    +0.10
    0.02
    24
    +0.10
    0.02
    Negative Logits
    lda
    -0.71
    Sov
    -0.71
    artisan
    -0.70
    asus
    -0.68
    kamp
    -0.67
    owitz
    -0.66
    ï¸ı
    -0.66
    AIDS
    -0.65
    Cub
    -0.65
    IRO
    -0.65
    POSITIVE LOGITS
    ity
    1.19
     occurrence
    0.93
    ization
    0.89
    cy
    0.88
     intervals
    0.88
    izing
    0.85
     ol
    0.84
    ities
    0.84
    ised
    0.84
    isation
    0.83
    Activations Density 0.058%

    No Known Activations