© 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. 8720
    Prev
    Next
    INDEX
    Explanations

    specific compounds and technical terms related to incidents and investigations

    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
    480
    +0.40
    2.0%
    481
    +0.19
    1.0%
    87
    +0.18
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.40
    0.07
    232
    +0.19
    0.06
    579
    +0.18
    0.06
    Negative Logits
    PDATE
    -0.70
    ilater
    -0.69
     undermin
    -0.69
    renheit
    -0.69
    glers
    -0.65
    akespe
    -0.62
     mathemat
    -0.62
     arrang
    -0.59
    behind
    -0.58
    NPR
    -0.58
    POSITIVE LOGITS
     Township
    0.88
     Islands
    0.87
     Profile
    0.84
     Heights
    0.83
     AFB
    0.80
     Brewing
    0.80
     County
    0.80
     Gardens
    0.74
     Peninsula
    0.73
     Island
    0.73
    Activations Density 0.271%

    No Known Activations