© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7421
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities or chances

    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
    608
    +0.12
    0.5%
    49
    +0.12
    0.5%
    665
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.06
    49
    +0.12
    0.06
    608
    +0.12
    0.06
    Negative Logits
     flows
    -0.74
    quickShipAvailable
    -0.74
     looms
    -0.72
     Explan
    -0.67
    advertising
    -0.65
    anes
    -0.64
     Direction
    -0.64
     costing
    -0.63
     Contin
    -0.62
    abiding
    -0.62
    POSITIVE LOGITS
     explore
    1.18
     indulge
    1.15
     learn
    1.13
     meet
    1.11
     observe
    1.10
     discuss
    1.09
     participate
    1.07
     introduce
    1.07
     partake
    1.06
     visit
    1.05
    Activations Density 0.163%

    No Known Activations