© 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. 41155
    Prev
    Next
    INDEX
    Explanations

    references to the Federal Reserve (Fed) and its activities

    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
    288
    +0.12
    0.5%
    699
    +0.11
    0.5%
    314
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.12
    0.01
    611
    +0.11
    0.01
    366
    +0.10
    0.01
    Negative Logits
     Sora
    -0.68
     Carbuncle
    -0.67
     Faw
    -0.66
    lust
    -0.65
     Monstrous
    -0.65
    ______
    -0.63
     Lebanese
    -0.63
    âĢ¢âĢ¢
    -0.63
    lihood
    -0.62
     Ange
    -0.62
    POSITIVE LOGITS
    erer
    1.09
    oras
    1.04
    ERAL
    0.98
    ered
    0.95
    ric
    0.93
    rik
    0.92
    liction
    0.92
    eli
    0.91
    ricular
    0.90
    rique
    0.90
    Activations Density 0.005%

    No Known Activations