© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of individuals or groups with names containing "Dem" or "dem" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to democracy and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    glers
    -0.73
     Doyle
    -0.59
     Holmes
    -0.58
     Harrington
    -0.58
    URN
    -0.58
     McGee
    -0.56
    ties
    -0.55
     PubMed
    -0.55
     HT
    -0.54
    WAYS
    -0.54
    POSITIVE LOGITS
    agogue
    1.35
    olition
    1.30
    ographically
    1.27
    agog
    1.27
    ocrat
    1.26
    eanor
    1.24
    psey
    1.20
    ographics
    1.18
    obil
    1.16
    aterial
    1.15
    Activations Density 0.022%

    No Known Activations