© 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. 11-RES-JB
    11. 5975
    Prev
    Next
    INDEX
    Explanations

    versions represented by numbers and punctuation

    oai_token-act-pair · gpt-3.5-turbo

    version numbers and release details of software updates

    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
    ennes
    -0.70
     Beir
    -0.66
    enza
    -0.60
    ruciating
    -0.60
    76561
    -0.59
    atu
    -0.58
     waged
    -0.57
     filibuster
    -0.57
    ĸļ
    -0.56
    itably
    -0.56
    POSITIVE LOGITS
    beta
    1.35
    rc
    1.15
    alpha
    1.08
    +.
    1.08
     beta
    1.06
     onwards
    1.04
     Beta
    1.00
    +,
    0.97
    Beta
    0.95
    çīĪ
    0.95
    Activations Density 0.037%

    No Known Activations