© 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. 2-RES-JB
    11. 19797
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "crutches."

    oai_token-act-pair · gpt-3.5-turbo

    the root "ut" as a recurring pattern or element in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flared
    -0.75
     flares
    -0.72
     proportions
    -0.66
     quarters
    -0.64
     gulf
    -0.63
     arisen
    -0.62
    cale
    -0.62
    ¯¯
    -0.61
     td
    -0.61
     compr
    -0.61
    POSITIVE LOGITS
    ierrez
    1.22
    ilitarian
    1.22
    anamo
    1.14
    tle
    1.09
    iful
    1.03
    ifully
    0.99
    opian
    0.98
    rition
    0.97
    ility
    0.97
    opia
    0.97
    Activations Density 0.013%

    No Known Activations