© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 11411
    Prev
    Next
    INDEX
    Explanations

    references to the concept of citizenship

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Citizens" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinned
    -0.71
     knife
    -0.69
    rained
    -0.67
    stab
    -0.67
     typing
    -0.65
     ladder
    -0.64
     upside
    -0.64
     healed
    -0.64
     crate
    -0.64
     dehyd
    -0.63
    POSITIVE LOGITS
     Citizens
    4.10
     Citizen
    2.94
    itizens
    2.30
    itizen
    1.68
    citizens
    1.60
     citizens
    1.53
     citizen
    1.49
     Citiz
    1.46
     Citizenship
    1.35
     Consumers
    1.35
    Activations Density 0.018%

    No Known Activations