© 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. 9-RES-JB
    11. 20784
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "Tw" followed by a number and possibly other characters

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific tokens or symbols related to a particular format or category

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¹ãĥĪ
    -0.78
    ãĥ£
    -0.74
    senal
    -0.73
    ++++++++++++++++
    -0.71
     PRESS
    -0.64
    ³³³³³³³³³³³³³³³³
    -0.63
     restricting
    -0.61
    tenance
    -0.59
     fracturing
    -0.58
     territorial
    -0.58
    POSITIVE LOGITS
    elfth
    1.36
    enty
    1.25
    elve
    1.23
    olves
    1.17
    ilight
    1.14
    inkle
    1.13
    erker
    1.13
    orld
    1.12
    erk
    1.12
    orks
    1.11
    Activations Density 0.024%

    No Known Activations