© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 20182
    Prev
    Next
    INDEX
    Explanations

    concepts related to privacy and legal statements

    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
    481
    +0.32
    1.6%
    480
    +0.30
    1.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.32
    0.08
    67
    +0.30
    0.07
    481
    +0.10
    0.11
    Negative Logits
    !.
    -0.82
    ."[
    -0.81
    ".[
    -0.80
    .[
    -0.76
    .<
    -0.75
    '.
    -0.75
    .""
    -0.74
    .).
    -0.73
    .'"
    -0.71
    .</
    -0.71
    POSITIVE LOGITS
    estern
    0.60
     )]
    0.56
    anchester
    0.56
    wealth
    0.51
    omic
    0.49
     afterlife
    0.47
    thood
    0.46
    ossus
    0.46
     virginity
    0.45
    zac
    0.45
    Activations Density 1.674%

    No Known Activations