© 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. 5552
    Prev
    Next
    INDEX
    Explanations

    informational cues such as section headings and advertisements within a text

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to "story" and "advertisement" in the text

    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
    cele
    -0.73
     Amit
    -0.63
     Imper
    -0.62
     monog
    -0.62
     cel
    -0.61
     unrecogn
    -0.60
    ste
    -0.60
     pri
    -0.59
    authent
    -0.58
    phen
    -0.58
    POSITIVE LOGITS
    iculty
    0.66
    espie
    0.66
    etary
    0.65
     Extras
    0.65
     VIDEOS
    0.64
    acters
    0.63
    yright
    0.63
    miah
    0.63
    ERY
    0.62
    iola
    0.62
    Activations Density 0.109%

    No Known Activations