© 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. 16099
    Prev
    Next
    INDEX
    Explanations

    phrases related to laws, regulations, and programs

    oai_token-act-pair · gpt-3.5-turbo

    references to legislation and regulatory frameworks

    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
    undy
    -0.76
     dresses
    -0.72
    unts
    -0.70
    itars
    -0.68
    uckles
    -0.66
     seams
    -0.65
     toes
    -0.65
     eyebrows
    -0.62
     alike
    -0.62
     castles
    -0.62
    POSITIVE LOGITS
     Advisory
    0.83
    Scan
    0.82
     Meter
    0.75
    2020
    0.73
     Clause
    0.73
    Pass
    0.73
     Fund
    0.73
     Difference
    0.73
    scan
    0.72
     Conservation
    0.72
    Activations Density 0.638%

    No Known Activations