© 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. 20155
    Prev
    Next
    INDEX
    Explanations

    references to testing and tests

    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
    218
    +0.11
    0.5%
    459
    +0.10
    0.5%
    62
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.11
    0.03
    519
    +0.10
    0.02
    460
    +0.09
    0.02
    Negative Logits
    ignt
    -0.77
    vernment
    -0.76
    theless
    -0.70
    VIDIA
    -0.66
    resent
    -0.66
     notor
    -0.65
    leans
    -0.65
    etheless
    -0.61
     peas
    -0.61
     Rove
    -0.60
    POSITIVE LOGITS
    osterone
    1.40
    imony
    1.39
    icles
    1.08
    imon
    1.08
    icular
    1.07
    udo
    1.06
    icle
    1.04
    ifies
    0.96
    aments
    0.90
    su
    0.89
    Activations Density 0.026%

    No Known Activations