© 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. 7696
    Prev
    Next
    INDEX
    Explanations

    information related to the weight (in grams or pounds) of objects

    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
    555
    +0.10
    0.5%
    497
    +0.10
    0.5%
    615
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    260
    +0.10
    0.03
    495
    +0.10
    0.02
    35
    +0.09
    0.02
    Negative Logits
    cknow
    -0.77
     Opportun
    -0.76
    otiation
    -0.75
    onal
    -0.70
    nect
    -0.69
    rupted
    -0.69
    repeat
    -0.68
    bys
    -0.66
    orate
    -0.66
    iphate
    -0.66
    POSITIVE LOGITS
     weighs
    1.22
     kilograms
    1.18
     lbs
    1.17
     pounds
    1.13
     ounces
    1.06
     bulky
    1.06
     weighing
    1.05
     weigh
    1.03
     weights
    1.03
    lbs
    1.02
    Activations Density 0.092%

    No Known Activations