© 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. 19448
    Prev
    Next
    INDEX
    Explanations

    concerns or conflicts related to ethics, positions of authority, or potential wrongdoings

    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
    459
    +0.15
    0.7%
    407
    +0.14
    0.7%
    497
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    -0.03
    368
    +0.14
    0.06
    459
    +0.10
    0.05
    Negative Logits
     adv
    -0.56
     Realms
    -0.54
    uster
    -0.54
    atical
    -0.53
    ionics
    -0.53
     viz
    -0.52
     innocuous
    -0.52
    ãĥ
    -0.51
    ibles
    -0.51
    isSpecialOrderable
    -0.50
    POSITIVE LOGITS
     similarly
    0.70
     similar
    0.67
    coni
    0.63
     these
    0.59
    velt
    0.58
    sylv
    0.58
     meanwhile
    0.56
    FontSize
    0.55
     unaffected
    0.55
     this
    0.54
    Activations Density 1.213%

    No Known Activations