© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 10313
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is speaking or expressing an opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate attribution or references to statements made by individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inary
    -0.77
    eneg
    -0.73
    rats
    -0.73
    acts
    -0.72
    leases
    -0.71
    venth
    -0.71
    ãĥĻ
    -0.70
    cffffcc
    -0.69
    rel
    -0.67
    apters
    -0.66
    POSITIVE LOGITS
     Jonathan
    0.89
     Joyce
    0.87
     David
    0.87
     Pamela
    0.86
     Laura
    0.84
     Katie
    0.83
     Jon
    0.83
     Ian
    0.82
     Diane
    0.81
     Polly
    0.81
    Activations Density 0.032%

    No Known Activations