© 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. 10998
    Prev
    Next
    INDEX
    Explanations

    terms related to intelligence, IQ, and cognitive ability

    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
    679
    +0.16
    0.7%
    356
    +0.11
    0.5%
    499
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.16
    0.02
    575
    +0.11
    0.02
    288
    +0.11
    0.02
    Negative Logits
     Soda
    -0.84
    soDeliveryDate
    -0.84
    href
    -0.74
    raine
    -0.72
    utz
    -0.70
     Bundy
    -0.70
    OURCE
    -0.68
    LOAD
    -0.66
    dule
    -0.65
    )=(
    -0.65
    POSITIVE LOGITS
     quot
    1.29
    elligent
    0.86
    elligence
    0.84
     IQ
    0.79
    IQ
    0.78
    ively
    0.75
    otle
    0.73
     enrichment
    0.70
     superiority
    0.70
    ibility
    0.69
    Activations Density 0.032%

    No Known Activations