© 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 EvalsExportsinterp-engineNEWAPI 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. 3415
    Prev
    Next
    INDEX
    Explanations

    numeric values, decimals or percentages

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation or formatting changes in the text

    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
    hene
    -0.85
    ividual
    -0.85
     mosqu
    -0.80
    utsche
    -0.74
     communication
    -0.70
    earchers
    -0.69
     pinpoint
    -0.68
     withdrawing
    -0.66
    sterdam
    -0.66
     econom
    -0.65
    POSITIVE LOGITS
    Appearances
    1.59
    Contents
    1.58
    Trivia
    1.57
    Characters
    1.50
    Gallery
    1.37
    pmwiki
    1.36
    Episode
    1.31
    Gameplay
    1.17
    Spoiler
    1.13
    Season
    1.13
    Activations Density 0.297%

    No Known Activations