© 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. 12-RES-JB
    11. 2498
    Prev
    Next
    INDEX
    Explanations

    words related to personal stories or experiences

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    occurrences of numerical data or references to time within narratives

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    liest
    -0.82
    :(
    -0.79
    "-
    -0.77
    -.
    -0.76
    "))
    -0.75
    -,
    -0.73
    apest
    -0.73
    -
    -0.71
    ror
    -0.71
    SourceFile
    -0.70
    POSITIVE LOGITS
     however
    1.45
     though
    1.20
     meanwhile
    0.93
     amid
    0.88
     moreover
    0.88
     after
    0.82
     despite
    0.81
     alas
    0.80
     amidst
    0.79
     according
    0.78
    Activations Density 0.311%

    No Known Activations