© 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. 20710
    Prev
    Next
    INDEX
    Explanations

    specific entities and terms such as 'wand' and 'translittere' and 'Rodman' or actions like 'rebuilding'

    oai_token-act-pair · gpt-3.5-turbo

    the presence of text breaks or empty sections in the document

    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
     Seym
    -0.80
     Vaugh
    -0.68
     Niet
    -0.66
    ayson
    -0.65
     Moroc
    -0.62
    enegger
    -0.59
     vulner
    -0.58
     Berm
    -0.58
    atever
    -0.58
     horizont
    -0.57
    POSITIVE LOGITS
    Ĥİ
    0.66
     ][
    0.62
     largeDownload
    0.61
     Reincarnated
    0.58
    \":
    0.56
    cloud
    0.54
    fml
    0.52
    gpu
    0.52
    displayText
    0.50
    zbollah
    0.50
    Activations Density 0.628%

    No Known Activations