© 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. 3125
    Prev
    Next
    INDEX
    Explanations

    information related to software development processes

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

    references to changes and new initiatives within organizations or projects

    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
     nodd
    -1.03
    ccording
    -1.00
    aditional
    -0.97
    eatures
    -0.89
     tiss
    -0.88
     practition
    -0.87
     proport
    -0.86
     destro
    -0.84
    ě
    -0.82
    ĕ
    -0.82
    POSITIVE LOGITS
     be
    0.76
     is
    0.76
     being
    0.68
    being
    0.66
     been
    0.66
    be
    0.65
     Be
    0.64
     was
    0.63
    abor
    0.60
     im
    0.60
    Activations Density 0.060%

    No Known Activations