© 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. 12-RES-JB
    11. 3659
    Prev
    Next
    INDEX
    Explanations

    numbers and technical terminology related to computers

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to organizations, legal terms, and concepts related to law and governance

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    Í
    -0.59
     whichever
    -0.59
     dips
    -0.56
    ichever
    -0.55
     shrug
    -0.54
     depends
    -0.54
     ÂŃ
    -0.53
    TPPStreamerBot
    -0.53
     aren
    -0.53
     doesn
    -0.52
    POSITIVE LOGITS
    senal
    0.76
    !.
    0.71
    .[
    0.70
    igslist
    0.67
    .#
    0.63
    .(
    0.62
     Acquisition
    0.60
    ().
    0.60
    .
    0.60
    isite
    0.60
    Activations Density 0.763%

    No Known Activations