© 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. 8759
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize or highlight specific points or ideas

    oai_token-act-pair · gpt-3.5-turbo

    terms that emphasize significant themes or points

    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
    agues
    -0.73
    queue
    -0.67
    iak
    -0.67
     externalToEVAOnly
    -0.66
     inhibitor
    -0.66
    ade
    -0.65
    inating
    -0.65
    adem
    -0.63
    finder
    -0.62
     Referred
    -0.61
    POSITIVE LOGITS
     how
    1.06
     shortcomings
    0.88
     what
    0.87
     why
    0.87
     sentiments
    0.86
    why
    0.86
     aspects
    0.85
     facets
    0.82
     inequalities
    0.81
     deficiencies
    0.81
    Activations Density 0.193%

    No Known Activations