© 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. 21675
    Prev
    Next
    INDEX
    Explanations

    version numbers represented with the format digit.digit.digit in text

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, especially related to software versions and releases

    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
    Lear
    -0.67
    ufact
    -0.65
    flame
    -0.61
     scrut
    -0.58
    nut
    -0.58
     brim
    -0.58
     rall
    -0.58
    URI
    -0.57
    ieth
    -0.57
     vested
    -0.57
    POSITIVE LOGITS
     Converted
    0.77
    bis
    0.75
     partName
    0.71
    isSpecialOrderable
    0.69
     Fiat
    0.65
     Apply
    0.65
     Married
    0.65
     <+
    0.64
     Slime
    0.64
    negie
    0.62
    Activations Density 0.065%

    No Known Activations