© 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. 45598
    Prev
    Next
    INDEX
    Explanations

    references to awards, particularly those related to exceptional achievements or recognition in various fields

    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
    27
    +0.11
    0.5%
    760
    +0.10
    0.5%
    747
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    747
    +0.11
    0.01
    537
    +0.10
    0.02
    284
    +0.10
    0.01
    Negative Logits
    xual
    -0.69
    ologically
    -0.67
    umatic
    -0.66
    yll
    -0.62
    avoid
    -0.61
    amera
    -0.60
    dule
    -0.59
     attachment
    -0.59
     Kag
    -0.59
    Newsletter
    -0.58
    POSITIVE LOGITS
     Sachs
    1.21
    ioxide
    0.91
    agos
    0.76
    tein
    0.74
    midt
    0.72
    Silver
    0.71
    estones
    0.70
    ppe
    0.69
    leon
    0.68
    ZE
    0.63
    Activations Density 0.054%

    No Known Activations