© 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 EvalsExportsinterp-engineNEWAPI 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. 9410
    Prev
    Next
    INDEX
    Explanations

    questions or statements expressing uncertainty or seeking clarification

    oai_token-act-pair · gpt-3.5-turbo

    topics related to significant questions or issues

    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
    arus
    -0.66
    nces
    -0.63
     Tik
    -0.61
    unctions
    -0.60
    rican
    -0.60
    liv
    -0.59
     MIS
    -0.59
    RANT
    -0.59
     ..............
    -0.57
     Cosponsors
    -0.57
    POSITIVE LOGITS
     involves
    0.67
    tains
    0.65
    ever
    0.60
     computing
    0.60
    mentioned
    0.59
    ISE
    0.58
     relates
    0.58
     captcha
    0.56
     ever
    0.56
     regards
    0.56
    Activations Density 0.407%

    No Known Activations