© 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 12288
    9. 8-RES_FS12288-JB
    11. 10754
    Prev
    Next
    INDEX
    Explanations

    phrases related to implementing measures or changes for improvement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    549
    +0.13
    0.6%
    566
    +0.11
    0.5%
    35
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.13
    0.01
    326
    +0.11
    0.01
    301
    +0.10
    0.01
    Negative Logits
     Borough
    -0.70
    INGS
    -0.67
     Occupations
    -0.66
     ($)
    -0.64
    UGH
    -0.60
     families
    -0.60
     Colleges
    -0.60
     Metropolitan
    -0.59
    ertodd
    -0.58
     Superintendent
    -0.58
    POSITIVE LOGITS
    vention
    1.46
    statement
    1.34
    stall
    1.32
    itialized
    1.21
    itial
    1.19
    forcer
    1.06
    hardt
    1.03
    visor
    1.01
    ventions
    1.00
    vision
    1.00
    Activations Density 0.057%

    No Known Activations