© 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. 20284
    Prev
    Next
    INDEX
    Explanations

    references to books and publications

    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
    393
    +0.10
    0.5%
    479
    +0.10
    0.5%
    385
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.10
    0.03
    479
    +0.10
    0.02
    145
    +0.10
    0.03
    Negative Logits
    omever
    -0.81
    amount
    -0.78
    aido
    -0.78
    gallery
    -0.76
    pressure
    -0.74
    bender
    -0.72
    depending
    -0.71
    pool
    -0.69
    poke
    -0.69
    ringe
    -0.68
    POSITIVE LOGITS
     Definitive
    1.38
     Forgotten
    1.23
     Complete
    1.08
     Unt
    1.07
     Monstrous
    1.05
     Hidden
    1.04
     Myth
    1.01
     Gathering
    1.00
     Role
    1.00
     Ideal
    0.98
    Activations Density 0.086%

    No Known Activations