© 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. 8-RES-JB
    11. 17686
    Prev
    Next
    INDEX
    Explanations

    locations or entities corresponding to the term "Sel" followed by a numeric value

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.74
    ALLY
    -0.74
    ItemTracker
    -0.72
    ELS
    -0.69
    FG
    -0.67
    olicy
    -0.66
    å£
    -0.65
    IRD
    -0.65
     nomine
    -0.64
    ERN
    -0.63
    POSITIVE LOGITS
    ved
    1.00
    enium
    0.99
    beck
    0.99
    inker
    0.98
    anguage
    0.97
    seys
    0.93
    zer
    0.93
    sea
    0.93
    vag
    0.92
    mer
    0.91
    Activations Density 0.017%

    No Known Activations