© 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 EvalsExportsAPI 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. 14898
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical treatments or remedies

    oai_token-act-pair · gpt-3.5-turbo

    key components and structural elements in a report or article

    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
    kered
    -0.75
    yip
    -0.68
    ERAL
    -0.68
    glers
    -0.66
    auri
    -0.63
    iff
    -0.62
    eal
    -0.62
    lehem
    -0.61
    oxide
    -0.59
    buquerque
    -0.58
    POSITIVE LOGITS
     S
    2.29
    S
    1.92
     s
    1.72
     SV
    1.24
     SQ
    1.23
     ss
    1.18
     SAP
    1.17
    s
    1.16
     SA
    1.16
     SAS
    1.13
    Activations Density 0.571%

    No Known Activations