© 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. 10971
    Prev
    Next
    INDEX
    Explanations

    prepositions and conjunctions

    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
    373
    +0.12
    0.6%
    242
    +0.11
    0.5%
    527
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.12
    0.02
    311
    +0.11
    0.01
    485
    +0.10
    0.01
    Negative Logits
     centrif
    -0.69
    ertodd
    -0.65
    Ô
    -0.62
     giveaway
    -0.59
     evaluations
    -0.59
     cx
    -0.57
     vortex
    -0.57
     redesign
    -0.57
     sidebar
    -0.55
     VK
    -0.55
    POSITIVE LOGITS
    course
    0.97
     whom
    0.84
     us
    0.83
     course
    0.78
    icial
    0.76
    ramer
    0.73
    Ĥ¬
    0.72
     kin
    0.68
     Tradable
    0.67
    hi
    0.67
    Activations Density 0.033%

    No Known Activations