© 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. 10133
    Prev
    Next
    INDEX
    Explanations

    names of authors, directors, and illustrators

    oai_token-act-pair · gpt-3.5-turbo

    names of authors and contributors in literature or media

    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
     convictions
    -0.71
     silence
    -0.67
    ccording
    -0.64
     judgments
    -0.64
     filibuster
    -0.64
     arrests
    -0.64
    20439
    -0.63
    ghazi
    -0.63
     object
    -0.62
     refusal
    -0.61
    POSITIVE LOGITS
     Architects
    1.26
     Productions
    0.99
    iets
    0.93
     Associates
    0.92
     Random
    0.80
     Studios
    0.78
     (#
    0.77
     QC
    0.76
     Graphics
    0.76
    orks
    0.75
    Activations Density 0.349%

    No Known Activations