© 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. 1-RES-JB
    11. 7382
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named "Dem"

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to the term "Dem" or its variants, likely indicating a focus on Democratic entities or themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.84
    glers
    -0.72
    olkien
    -0.71
    externalActionCode
    -0.71
    tips
    -0.70
    DAY
    -0.67
    =~=~
    -0.66
    lihood
    -0.65
    OUP
    -0.65
    ties
    -0.63
    POSITIVE LOGITS
    olition
    1.08
     Dem
    0.92
    agogue
    0.91
     unden
    0.91
    onym
    0.79
    agog
    0.78
    ecast
    0.77
    itri
    0.77
     strugg
    0.76
    onse
    0.73
    Activations Density 0.006%

    No Known Activations