© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22971
    Prev
    Next
    INDEX
    Explanations

    specific sections or entities within articles, blogs, or reports

    oai_token-act-pair · gpt-3.5-turbo

    references to articles, reports, and posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibles
    -0.65
     Remain
    -0.61
    vae
    -0.60
    yrics
    -0.59
    ãĤ¨ãĥ«
    -0.58
     ingred
    -0.57
     Lover
    -0.57
     minorities
    -0.56
    Reloaded
    -0.56
     missiles
    -0.55
    POSITIVE LOGITS
    spot
    0.73
     GOODMAN
    0.71
    endix
    0.69
     affiliate
    0.68
    athon
    0.68
    chet
    0.67
    alysis
    0.67
    gha
    0.65
    bush
    0.64
    folio
    0.63
    Activations Density 0.145%

    No Known Activations