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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17382
    Prev
    Next
    INDEX
    Explanations

    information related to legislation and legal matters

    oai_token-act-pair · gpt-3.5-turbo

    discussions around laws and regulations pertaining to sexual orientation and gender identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    byn
    -0.79
    oeuv
    -0.77
    yss
    -0.72
     Schwar
    -0.72
    selage
    -0.72
     Ital
    -0.72
     spo
    -0.71
    Lenin
    -0.70
    auri
    -0.70
     istg
    -0.70
    POSITIVE LOGITS
     legalized
    1.41
     enacted
    1.40
     decriminal
    1.35
     laws
    1.33
     statute
    1.31
     legalizing
    1.31
     ordinances
    1.30
     legalize
    1.30
     legisl
    1.30
     legislation
    1.29
    Activations Density 0.361%

    No Known Activations