© 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. 18149
    Prev
    Next
    INDEX
    Explanations

    terms related to interviews

    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
    679
    +0.14
    0.6%
    710
    +0.13
    0.6%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    710
    +0.14
    0.03
    679
    +0.13
    0.03
    641
    +0.10
    0.03
    Negative Logits
    axy
    -0.78
    math
    -0.77
    mil
    -0.72
    ciplinary
    -0.72
    blue
    -0.69
     Goods
    -0.68
     Haram
    -0.67
    DIV
    -0.65
    hover
    -0.64
    ectar
    -0.63
    POSITIVE LOGITS
    ees
    1.16
     interviews
    0.95
     interview
    0.95
     transcripts
    0.89
    ee
    0.88
     Transcript
    0.87
     subjects
    0.84
     conducted
    0.82
     Interview
    0.80
    ioned
    0.78
    Activations Density 0.033%

    No Known Activations