© 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. 9-RES-JB
    11. 1374
    Prev
    Next
    INDEX
    Explanations

    legal terms and section numbers within text

    oai_token-act-pair · gpt-3.5-turbo

    legal or formal references, specifically related to statutes and amendments

    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
    ï¸ı
    -0.77
    elight
    -0.76
    pictured
    -0.70
    Hidden
    -0.70
     Oops
    -0.68
     gigs
    -0.68
    killer
    -0.66
    texture
    -0.66
    araoh
    -0.64
    steen
    -0.63
    POSITIVE LOGITS
     pursuant
    1.33
     hereby
    1.33
     shall
    1.32
     subparagraph
    1.30
     practicable
    1.24
    shall
    1.20
     [[
    1.19
     applicable
    1.16
     ``(
    1.16
     subsection
    1.16
    Activations Density 0.831%

    No Known Activations