© 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. 7591
    Prev
    Next
    INDEX
    Explanations

    instances of struggle or challenge

    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
    90
    +0.11
    0.5%
    736
    +0.10
    0.5%
    720
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.11
    0.05
    761
    +0.10
    0.05
    555
    +0.09
    0.04
    Negative Logits
    eg
    -0.79
    ember
    -0.72
    mob
    -0.68
    .?
    -0.68
    âĢij
    -0.68
    acha
    -0.67
    urgical
    -0.67
    eria
    -0.67
    ena
    -0.67
    mp
    -0.67
    POSITIVE LOGITS
    ãĥ¥
    0.69
    theless
    0.69
     nonetheless
    0.69
     aside
    0.65
     unsus
    0.63
     only
    0.61
    iously
    0.60
     instead
    0.59
    ãĥ£
    0.57
    =]
    0.57
    Activations Density 0.263%

    No Known Activations