© 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. 9012
    Prev
    Next
    INDEX
    Explanations

    examples and discussions that involve details about machines and technical systems

    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
    393
    +0.13
    0.6%
    481
    +0.13
    0.6%
    720
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.13
    0.05
    43
    +0.13
    0.05
    375
    +0.11
    0.03
    Negative Logits
    ãĥ¥
    -0.80
    arily
    -0.68
    ļéĨĴ
    -0.65
    MpServer
    -0.65
    -,
    -0.65
    Detailed
    -0.64
    aled
    -0.63
    olves
    -0.61
    ioxide
    -0.60
    ħĭ
    -0.60
    POSITIVE LOGITS
     however
    1.28
     though
    1.07
     although
    0.89
     there
    0.82
     moreover
    0.79
     it
    0.78
     somew
    0.76
     according
    0.75
     we
    0.75
     yes
    0.74
    Activations Density 0.194%

    No Known Activations