© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6448
    Prev
    Next
    INDEX
    Explanations

    web links and references in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "p"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    é¾įåĸļ士
    -0.64
     Shining
    -0.63
    tan
    -0.62
     Exodus
    -0.62
     Pes
    -0.61
     unpaid
    -0.60
     kinderg
    -0.60
     referees
    -0.60
     Merry
    -0.60
     Lauder
    -0.59
    POSITIVE LOGITS
    okemon
    1.44
    ascal
    1.38
    ossible
    1.37
    redict
    1.29
    ulse
    1.29
    urchase
    1.25
    resents
    1.24
    ilot
    1.21
    olar
    1.21
    izza
    1.19
    Activations Density 0.035%

    No Known Activations