© 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. 5852
    Prev
    Next
    INDEX
    Explanations

    situations or contexts where someone or something benefits, whether economically, socially, or through a particular action

    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
    288
    +0.14
    0.6%
    679
    +0.12
    0.5%
    22
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    22
    +0.14
    0.02
    97
    +0.12
    0.02
    712
    +0.11
    0.01
    Negative Logits
     caul
    -0.65
     swirling
    -0.59
     residues
    -0.59
    body
    -0.58
    slice
    -0.57
     Hole
    -0.56
    çĦ
    -0.56
     mush
    -0.56
    rez
    -0.56
     ut
    -0.56
    POSITIVE LOGITS
     financially
    0.88
     greatly
    0.88
     enormously
    0.84
    iciary
    0.79
     immensely
    0.79
     tremendously
    0.78
    igan
    0.78
    benefit
    0.75
    Marginal
    0.75
    Reviewer
    0.75
    Activations Density 0.028%

    No Known Activations