© 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. 7-RES-JB
    11. 14270
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or certainty related to the presence or availability of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions denoting persistence or continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    buster
    -0.78
    strip
    -0.65
    friends
    -0.59
    fit
    -0.59
     sucks
    -0.58
     cursed
    -0.58
     pounded
    -0.57
    achi
    -0.56
    bil
    -0.56
     possessed
    -0.56
    POSITIVE LOGITS
     plenty
    0.90
     unanim
    0.88
     lots
    0.80
     disagreement
    0.73
     ambiguity
    0.73
    umption
    0.73
    omething
    0.73
    onnaissance
    0.72
     differences
    0.71
     LOT
    0.71
    Activations Density 0.092%

    No Known Activations