© 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. 6-RES-JB
    11. 19670
    Prev
    Next
    INDEX
    Explanations

    legal terms and references within a document

    oai_token-act-pair · gpt-3.5-turbo

    legal references to specific articles and sections of laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nanto
    -0.67
    eton
    -0.65
     pickup
    -0.64
     Hills
    -0.58
    ezvous
    -0.58
     Takeru
    -0.58
     interviewed
    -0.57
     mids
    -0.56
     RUN
    -0.56
     Mari
    -0.56
    POSITIVE LOGITS
     prohibition
    0.78
     Clause
    0.74
     entitled
    0.74
    venth
    0.73
    scribed
    0.73
    endment
    0.72
    hibited
    0.71
    :{
    0.70
    basic
    0.70
    hibition
    0.69
    Activations Density 0.057%

    No Known Activations