© 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. 1251
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and stories

    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
    240
    +0.13
    0.6%
    55
    +0.12
    0.5%
    715
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.13
    0.05
    598
    +0.12
    0.04
    715
    +0.11
    0.05
    Negative Logits
    saf
    -0.67
    "},"
    -0.66
    ski
    -0.63
    thro
    -0.62
    wreck
    -0.61
    halla
    -0.60
     CrossRef
    -0.58
    mast
    -0.58
    sk
    -0.58
    capt
    -0.58
    POSITIVE LOGITS
    oner
    1.07
    bered
    1.06
    ooo
    1.05
    oooo
    1.02
    oths
    0.97
    fter
    0.97
    apy
    0.93
    arin
    0.92
    othe
    0.88
     far
    0.88
    Activations Density 0.058%

    No Known Activations