© 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 24576
    9. 8-RES_FS24576-JB
    11. 11950
    Prev
    Next
    INDEX
    Explanations

    names or terms likely related to a specific family or dynasty

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.17
    0.8%
    569
    +0.10
    0.5%
    546
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.17
    -0.01
    232
    +0.10
    0.03
    659
    +0.10
    0.03
    Negative Logits
     tease
    -0.63
     envelope
    -0.63
    ACTED
    -0.61
     Heads
    -0.61
     flourish
    -0.59
    Princ
    -0.58
     fuse
    -0.56
     stocking
    -0.56
     pointer
    -0.55
     consequence
    -0.55
    POSITIVE LOGITS
    imura
    1.00
    illes
    0.92
    ulas
    0.91
    ivas
    0.91
    ula
    0.91
    onest
    0.88
    ter
    0.86
    icago
    0.86
    ilon
    0.85
    iba
    0.83
    Activations Density 0.060%

    No Known Activations