© 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. 3-RES-JB
    11. 8996
    Prev
    Next
    INDEX
    Explanations

    references to a specific bill or regulation labeled as "SB" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific legislative bill or statute, identified as "SB"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omorphic
    -0.76
    olate
    -0.66
    ghan
    -0.64
    cule
    -0.64
     Hiroshima
    -0.63
     plur
    -0.63
     ease
    -0.63
     clitor
    -0.63
     pastoral
    -0.62
     Dying
    -0.62
    POSITIVE LOGITS
    SB
    1.11
    ORTS
    0.90
     SB
    0.87
    ugg
    0.82
    IFF
    0.81
    UX
    0.81
    EED
    0.79
    JC
    0.78
    OUT
    0.77
    BM
    0.75
    Activations Density 0.008%

    No Known Activations