© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9014
    Prev
    Next
    INDEX
    Explanations

    direct speech dialogues

    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
    480
    +0.34
    2.2%
    373
    +0.27
    1.8%
    266
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    426
    +0.34
    0.08
    107
    +0.27
    0.07
    719
    +0.08
    0.08
    Negative Logits
     imprint
    -0.45
     liv
    -0.45
     horizont
    -0.44
     muse
    -0.43
     sacrific
    -0.42
     invention
    -0.41
     motif
    -0.41
     pyramid
    -0.41
     commem
    -0.41
     tremend
    -0.41
    POSITIVE LOGITS
    Ķ
    0.56
    ï¸ı
    0.55
    ľ
    0.55
    Ļ
    0.51
    CNN
    0.50
    ¦
    0.50
    ONSORED
    0.49
    Specifically
    0.49
    _>
    0.49
    said
    0.47
    Activations Density 0.580%

    No Known Activations