© 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. 20110
    Prev
    Next
    INDEX
    Explanations

    references to specific names or individuals

    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
    511
    +0.12
    0.5%
    481
    +0.10
    0.4%
    722
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.12
    0.06
    224
    +0.10
    0.06
    659
    +0.09
    0.05
    Negative Logits
    ggle
    -0.70
    ASED
    -0.65
    acts
    -0.64
    ctors
    -0.62
    ghai
    -0.62
    lance
    -0.62
    fare
    -0.61
    atical
    -0.61
    Examples
    -0.61
    SIGN
    -0.59
    POSITIVE LOGITS
    mith
    1.51
    '
    1.32
    hip
    1.30
    ullivan
    1.30
    hips
    1.29
    pring
    1.25
    ilver
    1.24
    kaya
    1.22
    hirt
    1.21
    chool
    1.19
    Activations Density 0.203%

    No Known Activations