© 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. 4670
    Prev
    Next
    INDEX
    Explanations

    references to trade-related information, specifically about goods like beans, rice, and ivory, as well as about military equipment

    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
    447
    +0.29
    1.4%
    481
    +0.20
    1.0%
    84
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.09
    537
    +0.20
    0.07
    575
    +0.11
    0.08
    Negative Logits
    lishes
    -0.69
     repetition
    -0.64
     rapport
    -0.61
     narrator
    -0.60
     noise
    -0.60
    ĪĴ
    -0.60
    erate
    -0.59
    unct
    -0.59
    cknow
    -0.57
    ongevity
    -0.57
    POSITIVE LOGITS
     cheaply
    1.00
     abroad
    0.92
     illegally
    0.89
     licences
    0.84
     valued
    0.83
     from
    0.82
     destined
    0.81
    coins
    0.80
     belonging
    0.79
     supplies
    0.78
    Activations Density 0.484%

    No Known Activations