© 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. 17847
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a refusal or lack of obligation

    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
    +0.26
    1.2%
    351
    +0.10
    0.5%
    411
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    351
    +0.26
    0.06
    762
    +0.10
    0.09
    411
    +0.10
    0.06
    Negative Logits
     ITS
    -0.64
     unsurprisingly
    -0.64
     respectively
    -0.61
     predictably
    -0.61
     omin
    -0.59
    their
    -0.59
    WARE
    -0.56
    Elsewhere
    -0.56
     Their
    -0.55
    EMS
    -0.55
    POSITIVE LOGITS
     myself
    1.47
     my
    0.91
     âĢ¦"
    0.86
     ['
    0.84
     fuckin
    0.83
     sacrific
    0.79
     [
    0.78
    ),"
    0.77
    %"
    0.76
    ,'"
    0.76
    Activations Density 0.754%

    No Known Activations