© 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. 24121
    Prev
    Next
    INDEX
    Explanations

    questions and statements of disbelief or surprise

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.10
    0.5%
    742
    +0.10
    0.4%
    371
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.06
    285
    +0.10
    0.03
    591
    +0.09
    0.03
    Negative Logits
    etheless
    -0.73
    awei
    -0.72
    prisingly
    -0.71
    ometimes
    -0.69
    ricanes
    -0.66
    surprisingly
    -0.64
    uitive
    -0.63
    ãĤ´ãĥ³
    -0.63
     quir
    -0.61
    æ©
    -0.61
    POSITIVE LOGITS
    '"
    1.73
    .")
    1.55
    ]"
    1.49
    >"
    1.45
    }"
    1.45
    ',"
    1.45
    ")
    1.43
    "]
    1.43
    ").
    1.42
     ..."
    1.40
    Activations Density 0.285%

    No Known Activations