© 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. 1-RES-JB
    11. 13256
    Prev
    Next
    INDEX
    Explanations

    terms related to book awards, specifically the Booker Prize

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the name "Booker."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATIONAL
    -0.80
    ivot
    -0.71
    remlin
    -0.70
    UAL
    -0.69
    arching
    -0.68
    ationally
    -0.64
    ospital
    -0.64
    laus
    -0.63
    ixed
    -0.63
     holiest
    -0.63
    POSITIVE LOGITS
     Booker
    1.45
     absor
    0.82
     Compan
    0.79
    \\\\\\\\
    0.78
    stown
    0.76
    ventus
    0.75
    berries
    0.75
    jee
    0.71
    stall
    0.70
    vill
    0.69
    Activations Density 0.004%

    No Known Activations