© 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 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. 9-RES-JB
    11. 18205
    Prev
    Next
    INDEX
    Explanations

    legal and regulatory terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal or regulatory topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adj
    -0.80
    à¼
    -0.78
    seed
    -0.77
    nis
    -0.75
     teasp
    -0.73
    vous
    -0.70
    retty
    -0.70
    Written
    -0.70
    appointed
    -0.69
    orah
    -0.68
    POSITIVE LOGITS
     legality
    0.86
     accessibility
    0.86
     whether
    0.85
     localization
    0.85
     refunds
    0.84
     topics
    0.84
     aspects
    0.83
     sexuality
    0.80
     issues
    0.80
     finances
    0.79
    Activations Density 0.087%

    No Known Activations