© 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. 19608
    Prev
    Next
    INDEX
    Explanations

    specific terms related to success or outcomes, such as "known," "sufficient," "turn out," "import," "underestimating," or "deep."

    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
    509
    +0.13
    0.6%
    240
    +0.13
    0.6%
    438
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.13
    0.05
    214
    +0.13
    0.04
    509
    +0.10
    0.04
    Negative Logits
     âĢ¦"
    -0.65
     groove
    -0.62
     ðŁĻĤ
    -0.61
     ..."
    -0.60
    dies
    -0.59
     https
    -0.58
    )",
    -0.57
    ..."
    -0.57
     bench
    -0.56
    âĢ¦"
    -0.56
    POSITIVE LOGITS
    surprisingly
    1.07
    entimes
    1.06
    ifully
    1.05
    ensibly
    1.03
    sequently
    1.02
    inarily
    0.98
    quartered
    0.98
    rarily
    0.96
    ificantly
    0.94
    lying
    0.94
    Activations Density 0.255%

    No Known Activations