© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    personal information and legal terms related to citizenship and identity

    oai_token-act-pair · gpt-3.5-turbo

    references to citizenship and nationality issues

    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
     Crate
    -0.84
    seless
    -0.79
    worst
    -0.79
     pessimistic
    -0.73
    tank
    -0.71
    warm
    -0.70
     crate
    -0.70
     glut
    -0.69
    Boss
    -0.69
     distraction
    -0.69
    POSITIVE LOGITS
     citizenship
    1.78
     Citizenship
    1.71
     registration
    1.49
     passports
    1.42
     residency
    1.41
     registrations
    1.40
     Registration
    1.38
     registry
    1.38
     baptism
    1.37
     eligibility
    1.36
    Activations Density 0.588%

    No Known Activations