© 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. 7-RES-JB
    11. 1691
    Prev
    Next
    INDEX
    Explanations

    specific references to a location named "El."

    oai_token-act-pair · gpt-3.5-turbo

    references to "El" followed by a name or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.75
    NOW
    -0.62
    ãģĨ
    -0.62
    LESS
    -0.61
    henko
    -0.61
    matter
    -0.61
    é¾įå¥ij士
    -0.60
     Telesc
    -0.59
    ICLE
    -0.58
    manship
    -0.58
    POSITIVE LOGITS
    abor
    1.11
     Paso
    1.08
    igible
    1.07
    azer
    1.02
    usive
    1.02
    iza
    1.01
     Salvador
    0.95
     Niño
    0.94
    apsed
    0.94
    ving
    0.92
    Activations Density 0.017%

    No Known Activations