© 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 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. 0-RES-JB
    11. 1969
    Prev
    Next
    INDEX
    Explanations

    numeric quantities with the word "single" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to singles and their performance or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atell
    -0.77
     Schr
    -0.70
     Enlightenment
    -0.70
     Fedora
    -0.70
    integ
    -0.70
     Andromeda
    -0.69
    ãĥ´
    -0.69
     Canaver
    -0.68
    elect
    -0.67
     Farn
    -0.66
    POSITIVE LOGITS
     singles
    2.04
     reserves
    1.79
     reserve
    1.59
    erred
    1.50
     unused
    1.46
     cas
    1.31
     deferred
    1.13
     stud
    1.06
    bucks
    1.04
     reservoirs
    0.95
    Activations Density 0.029%

    No Known Activations