© 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. 11-RES-JB
    11. 320
    Prev
    Next
    INDEX
    Explanations

    references to political figures or actions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lawy
    -0.68
     detrim
    -0.65
     antioxid
    -0.65
     thumbs
    -0.65
     professionals
    -0.63
     strikeouts
    -0.63
     scissors
    -0.62
     chimpanzees
    -0.61
     gigs
    -0.61
     mornings
    -0.60
    POSITIVE LOGITS
    ation
    1.77
    ification
    1.55
    ations
    1.51
    ions
    1.49
    als
    1.49
    icity
    1.48
    ion
    1.47
    ate
    1.45
    ics
    1.44
    ic
    1.44
    Activations Density 0.729%

    No Known Activations