© 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. 10-RES-JB
    11. 7084
    Prev
    Next
    INDEX
    Explanations

    references to reports or studies

    oai_token-act-pair · gpt-3.5-turbo

    specific references to official reports and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agogue
    -0.88
    æ©
    -0.81
    twitch
    -0.75
     masc
    -0.72
    Fans
    -0.70
     vending
    -0.69
    pot
    -0.68
    lane
    -0.68
    locks
    -0.67
     Craigslist
    -0.67
    POSITIVE LOGITS
     report
    1.60
     Report
    1.44
     findings
    1.38
    Report
    1.32
     damning
    1.32
    report
    1.25
     scathing
    1.25
     audit
    1.23
     conclusions
    1.23
     recommendations
    1.21
    Activations Density 0.496%

    No Known Activations