© 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. 8647
    Prev
    Next
    INDEX
    Explanations

    words related to surnames

    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
    683
    +0.14
    0.7%
    216
    +0.09
    0.4%
    23
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    683
    +0.14
    0.03
    26
    +0.09
    0.03
    763
    +0.09
    0.02
    Negative Logits
    s
    -0.77
    ĸļ
    -0.69
    scl
    -0.66
    ertodd
    -0.66
     Lovecraft
    -0.61
    VIDIA
    -0.59
     disadvant
    -0.58
    acebook
    -0.57
    e
    -0.57
    atform
    -0.57
    POSITIVE LOGITS
    jee
    1.17
    idge
    1.01
    adish
    0.96
    unning
    0.95
    lein
    0.90
    rors
    0.90
    nery
    0.90
    ror
    0.86
    aton
    0.85
    rett
    0.84
    Activations Density 0.061%

    No Known Activations