© 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. 7-RES-JB
    11. 14710
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific product or organization denoted by "CB."

    oai_token-act-pair · gpt-3.5-turbo

    references to chemical and biological warfare agents

    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
    aciously
    -0.73
    wine
    -0.68
     Gors
    -0.67
    umerable
    -0.66
    arily
    -0.64
    orio
    -0.63
    perse
    -0.63
     Gutenberg
    -0.62
     Tigers
    -0.61
     Maid
    -0.61
    POSITIVE LOGITS
    rief
    0.82
    dar
    0.78
    QB
    0.76
    ASE
    0.76
    anut
    0.75
    GB
    0.73
    ody
    0.73
    oard
    0.72
    STAR
    0.72
    SA
    0.69
    Activations Density 0.018%

    No Known Activations