© 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. 45527
    Prev
    Next
    INDEX
    Explanations

    various forms and derivatives of the word "fire."

    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
    496
    +0.16
    0.7%
    373
    +0.11
    0.5%
    726
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.16
    0.01
    464
    +0.11
    0.01
    110
    +0.10
    0.01
    Negative Logits
    ĸļ
    -0.79
    sylv
    -0.77
    iple
    -0.73
    onent
    -0.72
    ociated
    -0.69
    imore
    -0.69
    insula
    -0.67
    ermott
    -0.66
    iances
    -0.66
    acca
    -0.66
    POSITIVE LOGITS
    lli
    1.35
    nces
    1.21
    tta
    1.17
    tto
    1.13
    lda
    1.05
    nder
    1.04
    lla
    1.02
    llo
    0.99
    nce
    0.98
    ttes
    0.96
    Activations Density 0.012%

    No Known Activations