© 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 EvalsExportsinterp-engineNEWAPI 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. 14511
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and instructions

    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
    73
    +0.09
    0.4%
    573
    +0.09
    0.4%
    189
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.09
    0.07
    73
    +0.09
    0.05
    128
    +0.08
    0.04
    Negative Logits
    Were
    -0.77
    ãĥĵ
    -0.73
    vered
    -0.71
    oken
    -0.71
    ħĭ
    -0.70
    were
    -0.70
    estern
    -0.70
    staff
    -0.68
    minent
    -0.68
    ntil
    -0.67
    POSITIVE LOGITS
     incorporates
    1.42
     promotes
    1.42
     replaces
    1.42
     provides
    1.40
     integrates
    1.40
     gives
    1.40
     enhances
    1.39
     eliminates
    1.38
     protects
    1.37
     regulates
    1.36
    Activations Density 0.640%

    No Known Activations