© 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. 17827
    Prev
    Next
    INDEX
    Explanations

    statements related to personal identity and opinions

    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
    514
    +0.11
    0.5%
    759
    +0.11
    0.5%
    621
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    514
    +0.11
    0.17
    759
    +0.11
    0.16
    352
    +0.10
    0.16
    Negative Logits
    çīĪ
    -0.78
     fortun
    -0.74
     snacks
    -0.74
     seiz
    -0.71
     ACS
    -0.65
     Sok
    -0.65
     publicity
    -0.65
     sights
    -0.65
     Objective
    -0.65
     Circus
    -0.65
    POSITIVE LOGITS
    Ļ
    1.38
    ¤
    1.28
    ¬
    1.25
    ª
    1.21
    ħ
    1.16
    Ķ
    1.15
    Ĵ
    1.15
    £
    1.14
    ĸ
    1.14
    ¼
    1.12
    Activations Density 0.245%

    No Known Activations