© 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. 4644
    Prev
    Next
    INDEX
    Explanations

    options or choices presented within a set of instructions, with a focus on actions to take in a specific situation

    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
    101
    +0.13
    0.6%
    754
    +0.11
    0.5%
    160
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    754
    +0.13
    0.02
    435
    +0.11
    0.02
    485
    +0.09
    0.02
    Negative Logits
    grave
    -0.78
    mind
    -0.76
    soever
    -0.73
    ritic
    -0.67
    nces
    -0.67
    hemat
    -0.65
    tub
    -0.65
    urst
    -0.65
    friend
    -0.63
    anti
    -0.62
    POSITIVE LOGITS
     options
    1.00
     option
    0.94
    atives
    0.80
    finder
    0.80
     choices
    0.77
     Option
    0.76
    ality
    0.75
    Option
    0.74
    nels
    0.74
    alities
    0.74
    Activations Density 0.024%

    No Known Activations