© 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. 26827
    Prev
    Next
    INDEX
    Explanations

    reported speech and statements made by individuals within the text

    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
    745
    +0.12
    0.5%
    425
    +0.11
    0.5%
    514
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.05
    417
    +0.11
    0.04
    679
    +0.10
    0.05
    Negative Logits
    Eva
    -0.76
    Jews
    -0.63
     existential
    -0.62
    اÙĦ
    -0.62
    Brexit
    -0.61
    RFC
    -0.60
    LET
    -0.58
    selves
    -0.58
    ×IJ
    -0.58
    à¦
    -0.58
    POSITIVE LOGITS
    veland
    0.77
    aley
    0.75
     Thursday
    0.72
     Proced
    0.71
     Tuesday
    0.71
     Wednesday
    0.70
     Grounds
    0.69
     Superintendent
    0.69
     Graves
    0.69
     Friday
    0.66
    Activations Density 0.170%

    No Known Activations