© 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. 7765
    Prev
    Next
    INDEX
    Explanations

    instances of the word "survey" and related words like "surveyed", "surveying", etc

    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%
    447
    +0.12
    0.5%
    751
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    751
    +0.14
    0.02
    651
    +0.12
    0.02
    235
    +0.10
    0.02
    Negative Logits
    burning
    -0.70
     chopping
    -0.68
     curry
    -0.64
    iris
    -0.64
    mph
    -0.64
    cream
    -0.62
     slic
    -0.61
    vernment
    -0.61
     reserves
    -0.60
     Leilan
    -0.59
    POSITIVE LOGITS
     respondents
    0.96
     conducted
    0.93
     survey
    0.91
     respondent
    0.91
    ors
    0.88
    oral
    0.84
     surveys
    0.81
    naire
    0.78
     methodology
    0.76
     booths
    0.76
    Activations Density 0.024%

    No Known Activations