© 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. 3-RES-JB
    11. 470
    Prev
    Next
    INDEX
    Explanations

    references to legal permits in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to permits or licensing requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tone
    -0.76
    swick
    -0.72
     Chrom
    -0.72
    corn
    -0.72
    raped
    -0.72
    kaya
    -0.71
    angular
    -0.68
    cup
    -0.67
    tal
    -0.65
    enegger
    -0.65
    POSITIVE LOGITS
    Reviewer
    1.02
     permits
    0.99
     holders
    0.93
     permit
    0.93
     waivers
    0.89
     permitting
    0.86
     licenses
    0.86
     approvals
    0.85
     exemptions
    0.83
     compr
    0.83
    Activations Density 0.018%

    No Known Activations