© 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. 2-RES-JB
    11. 7769
    Prev
    Next
    INDEX
    Explanations

    strings of gibberish characters with a period at the end

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     corrid
    -0.79
    ometimes
    -0.77
    enhagen
    -0.74
     enthusi
    -0.72
     caucuses
    -0.72
     confir
    -0.68
     warr
    -0.68
     glim
    -0.67
    ecause
    -0.66
     suspic
    -0.65
    POSITIVE LOGITS
    sic
    0.72
    esp
    0.69
    vim
    0.67
     Regist
    0.67
     Sty
    0.66
    ensis
    0.66
     Tibetan
    0.65
    kun
    0.65
     Oss
    0.65
    vous
    0.63
    Activations Density 1.736%

    No Known Activations