© 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. 45774
    Prev
    Next
    INDEX
    Explanations

    definitions and attributes of various concepts and entities

    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
    388
    +0.11
    0.5%
    692
    +0.10
    0.5%
    481
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    692
    +0.11
    0.03
    55
    +0.10
    0.03
    102
    +0.10
    0.03
    Negative Logits
     Legions
    -0.76
     directions
    -0.71
     Universities
    -0.69
    osate
    -0.67
    PDATE
    -0.64
     Pers
    -0.64
     sands
    -0.63
     mathemat
    -0.63
    luster
    -0.61
     Prairie
    -0.60
    POSITIVE LOGITS
     ALWAYS
    0.84
    agraph
    0.83
    typically
    0.82
     usually
    0.78
     necessarily
    0.78
     inherently
    0.77
     ordinarily
    0.76
     capable
    0.76
    agonist
    0.74
    ermanent
    0.74
    Activations Density 0.138%

    No Known Activations