© 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. 4150
    Prev
    Next
    INDEX
    Explanations

    mentions of specific items or entities being marked or ranked

    oai_token-act-pair · gpt-3.5-turbo

    attributes related to rankings and performance

    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
     anew
    -0.61
    ummer
    -0.59
    Newsletter
    -0.53
     Weeks
    -0.52
     stabilize
    -0.47
    -,
    -0.44
     hemor
    -0.44
     --
    -0.44
     antic
    -0.43
    ,...
    -0.42
    POSITIVE LOGITS
    atsuki
    0.59
     lyrics
    0.58
     vocals
    0.56
     homophobic
    0.55
     Cosponsors
    0.55
     clitor
    0.54
    texture
    0.53
     pupils
    0.53
    ãĥ¡
    0.51
     UKIP
    0.51
    Activations Density 1.803%

    No Known Activations