© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 24287
    Prev
    Next
    INDEX
    Explanations

    terms related to the prefix "trans-" referring to across, beyond, through, or changing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to 'trans' in various contexts, such as transmittable diseases, transphobia, transgender issues, and trans fats

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Pledge
    -0.68
     Solitaire
    -0.68
     Maker
    -0.67
    lihood
    -0.64
     Sunder
    -0.63
     Bard
    -0.62
    ously
    -0.61
     maker
    -0.60
     Spo
    -0.60
     Flavoring
    -0.60
    POSITIVE LOGITS
    gression
    1.41
    mitt
    1.41
    continental
    1.32
    vest
    1.32
    posed
    1.25
    atlantic
    1.24
    gressive
    1.21
    figured
    1.19
    national
    1.16
    istors
    1.14
    Activations Density 0.015%

    No Known Activations