© 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. 12279
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical or introspective musings and observations

    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
    659
    +0.14
    0.6%
    154
    +0.10
    0.5%
    163
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.03
    335
    +0.10
    0.03
    154
    +0.09
    0.03
    Negative Logits
     Illum
    -0.65
    ãĥ´ãĤ¡
    -0.63
    doors
    -0.62
     Fargo
    -0.59
     Norn
    -0.59
    ãĤª
    -0.58
     Deadline
    -0.57
    IUM
    -0.57
     Calder
    -0.57
     DeVos
    -0.57
    POSITIVE LOGITS
    igsaw
    1.33
    umbo
    1.29
    ockey
    1.27
    agged
    1.24
    ingle
    1.19
    okers
    1.18
    anky
    1.18
    umbled
    1.16
    okingly
    1.16
    ammers
    1.15
    Activations Density 0.022%

    No Known Activations