© 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. 9-RES-JB
    11. 9900
    Prev
    Next
    INDEX
    Explanations

    universities and research institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and research entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    problem
    -0.69
    acci
    -0.69
    Ò
    -0.67
    arial
    -0.65
    orate
    -0.65
    ificate
    -0.65
    range
    -0.63
    cients
    -0.63
     FML
    -0.63
    )",
    -0.62
    POSITIVE LOGITS
     founder
    1.25
     CEO
    1.12
     frontman
    1.08
     analyst
    1.02
     director
    1.01
     chairman
    1.00
     columnist
    1.00
     alum
    0.99
     reporter
    0.97
     spokesman
    0.97
    Activations Density 0.414%

    No Known Activations