© 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. 6-RES-JB
    11. 8475
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gradle" with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Gradle."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shack
    -0.79
     Hole
    -0.72
    ħĭ
    -0.72
     Whale
    -0.63
     praying
    -0.63
    doors
    -0.61
     Cheney
    -0.61
     Role
    -0.61
     nesting
    -0.60
    BOOK
    -0.59
    POSITIVE LOGITS
    uates
    1.43
    uations
    1.28
    uation
    1.24
    uated
    1.20
    uating
    1.18
    uate
    1.09
    ients
    1.08
    iate
    1.03
    iferation
    0.93
    ient
    0.92
    Activations Density 0.024%

    No Known Activations