© 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. 317
    Prev
    Next
    INDEX
    Explanations

    terms related to microscopy and medical imaging techniques

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to biological processes and optical techniques

    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
    iquette
    -0.77
     Salvation
    -0.76
    LGBT
    -0.69
     booze
    -0.67
     lounge
    -0.64
    Ire
    -0.64
    deal
    -0.63
     perks
    -0.62
     patriotism
    -0.61
     paycheck
    -0.61
    POSITIVE LOGITS
     âĪ¼
    1.16
     molecular
    1.09
     morphology
    1.00
     computational
    1.00
     nucle
    0.96
     genomic
    0.95
     quantitative
    0.95
     theoret
    0.94
     Î
    0.94
     assay
    0.94
    Activations Density 1.159%

    No Known Activations