© 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. 2009
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Witt"

    oai_token-act-pair · gpt-3.5-turbo

    the mention of the name "Sitt" in various contexts

    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
     Gan
    -0.66
     Blazers
    -0.63
     location
    -0.62
     marks
    -0.62
     rope
    -0.61
     zone
    -0.60
     panel
    -0.60
     circle
    -0.59
     substitute
    -0.58
     generator
    -0.58
    POSITIVE LOGITS
    itt
    4.37
    ITT
    2.18
    ittle
    1.93
    itta
    1.84
    itty
    1.71
    itte
    1.66
    ett
    1.52
    itton
    1.49
    ittens
    1.45
    ittal
    1.42
    Activations Density 0.021%

    No Known Activations