© 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
    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. 1549
    Prev
    Next
    INDEX
    Explanations

    references to Wikipedia

    oai_token-act-pair · gpt-3.5-turbo

    references to Wikipedia and related educational content

    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
    taboola
    -0.74
    pring
    -0.71
    rums
    -0.70
    roach
    -0.68
    sbm
    -0.66
    gs
    -0.65
    ayed
    -0.65
    stra
    -0.65
    rine
    -0.64
    kamp
    -0.64
    POSITIVE LOGITS
    ipedia
    1.15
     Commons
    1.15
    Leaks
    1.04
    wiki
    0.95
     encyclopedia
    0.95
     Britann
    0.89
    pedia
    0.88
    UTC
    0.86
    Wikipedia
    0.85
     edits
    0.82
    Activations Density 0.038%

    No Known Activations