© 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. 14779
    Prev
    Next
    INDEX
    Explanations

    news stories to share

    oai_token-act-pair · gpt-3.5-turbo

    references to sharing or highlighting specific stories

    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
     Maid
    -0.71
    asers
    -0.66
    uctor
    -0.62
    icion
    -0.61
    hib
    -0.60
    ighed
    -0.59
     Ow
    -0.58
    iaries
    -0.58
    mens
    -0.56
    omore
    -0.56
    POSITIVE LOGITS
    ãĥĨãĤ£
    0.72
    illian
    0.68
     ..........
    0.67
    enaries
    0.66
    Community
    0.63
    ...]
    0.62
     ARTICLE
    0.61
     CONTR
    0.60
     WITHOUT
    0.60
    ebin
    0.59
    Activations Density 0.036%

    No Known Activations