© 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 EvalsExportsinterp-engineNEWAPI 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. 4743
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or providing ideas for change

    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
    718
    +0.14
    0.6%
    665
    +0.14
    0.6%
    186
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.14
    0.07
    718
    +0.14
    0.06
    49
    +0.12
    0.06
    Negative Logits
    gradient
    -0.75
    Orig
    -0.70
    croft
    -0.66
    til
    -0.66
    quickShipAvailable
    -0.64
    paren
    -0.63
    fixed
    -0.61
     Transcript
    -0.61
     è£ıè¦ļéĨĴ
    -0.60
    SpaceEngineers
    -0.60
    POSITIVE LOGITS
     donate
    1.32
     participate
    1.32
     partake
    1.22
     submit
    1.19
     gather
    1.18
     beware
    1.17
     undertake
    1.16
     emulate
    1.16
     contribute
    1.12
     join
    1.12
    Activations Density 0.185%

    No Known Activations