© 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. 11-RES-JB
    11. 14954
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "well."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "as well as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auri
    -0.68
    psc
    -0.63
    ppo
    -0.62
    oret
    -0.62
    akov
    -0.59
    ework
    -0.57
    uti
    -0.57
    ovo
    -0.56
    grain
    -0.56
    ``
    -0.55
    POSITIVE LOGITS
     as
    1.20
     AS
    0.68
     As
    0.64
    as
    0.64
    As
    0.58
     occasional
    0.53
    nesses
    0.50
     serve
    0.50
    ãĤ¯
    0.48
    inda
    0.48
    Activations Density 0.042%

    No Known Activations