© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 45790
    Prev
    Next
    INDEX
    Explanations

    references to various types of individuals, particularly focusing on the average or typical person in different contexts

    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
    302
    +0.12
    0.5%
    219
    +0.11
    0.5%
    715
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    660
    +0.12
    0.03
    91
    +0.11
    0.03
    302
    +0.11
    0.03
    Negative Logits
    otropic
    -0.76
    itars
    -0.72
     divisions
    -0.70
    ounding
    -0.66
     Shards
    -0.65
     disband
    -0.64
     overlapping
    -0.64
    acements
    -0.63
     subsidiaries
    -0.62
     giants
    -0.62
    POSITIVE LOGITS
     knows
    1.06
     instinctively
    0.96
     understands
    0.96
     who
    0.93
     learns
    0.90
     beware
    0.89
     realizes
    0.86
    who
    0.85
     thinks
    0.83
     expects
    0.81
    Activations Density 0.126%

    No Known Activations