© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2094
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Hannibal"

    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
    114
    +0.15
    0.7%
    7
    +0.14
    0.7%
    459
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.15
    0.02
    31
    +0.14
    0.02
    7
    +0.13
    0.02
    Negative Logits
    lda
    -0.90
    nces
    -0.72
    ngth
    -0.66
    graded
    -0.63
    externalActionCode
    -0.62
     logger
    -0.60
    geoning
    -0.60
    rero
    -0.60
    senal
    -0.60
    grading
    -0.57
    POSITIVE LOGITS
    ihil
    1.34
    ihilation
    1.26
    abis
    1.21
    ibal
    1.19
    iversary
    1.18
    igans
    1.03
    igan
    1.00
    enberg
    0.99
    apolis
    0.98
    unciation
    0.95
    Activations Density 0.020%

    No Known Activations