© 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. 7513
    Prev
    Next
    INDEX
    Explanations

    a mix of Arabic and Romanian text

    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
    231
    +0.11
    0.5%
    662
    +0.10
    0.4%
    406
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.11
    0.02
    406
    +0.10
    0.01
    488
    +0.10
    0.01
    Negative Logits
     GOODMAN
    -0.68
     charism
    -0.66
     Sparkle
    -0.61
     relevance
    -0.60
     Venezuel
    -0.58
     NPCs
    -0.57
     fascination
    -0.56
     Settlement
    -0.56
     contraceptive
    -0.55
    baugh
    -0.55
    POSITIVE LOGITS
    é¾įåĸļ士
    1.02
    ontent
    0.99
    ÏĦ
    0.93
    ı
    0.84
    ãĥ¥
    0.82
    ï¸ı
    0.82
    pt
    0.81
    ime
    0.81
    par
    0.81
    Ct
    0.80
    Activations Density 0.016%

    No Known Activations