© 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. 13804
    Prev
    Next
    INDEX
    Explanations

    political and organizational spokesperson titles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to spokespeople or representation in various contexts

    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
     Scotia
    -0.66
     circumstance
    -0.66
     submission
    -0.62
     exception
    -0.61
     jurisdiction
    -0.60
     adj
    -0.60
    's
    -0.60
     Germ
    -0.60
     citation
    -0.58
     differential
    -0.58
    POSITIVE LOGITS
    hips
    1.95
    hip
    1.90
    creen
    1.66
    pace
    1.62
    uits
    1.57
    manship
    1.51
    hops
    1.50
    pan
    1.48
    uit
    1.48
    peed
    1.47
    Activations Density 0.345%

    No Known Activations