© 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 EvalsExportsinterp-engineNEWAPI 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. 21113
    Prev
    Next
    INDEX
    Explanations

    phrases that end with "ff"

    oai_token-act-pair · gpt-3.5-turbo

    references to the character "Scoff" and variations like "Kauffman" or "Leffingwell."

    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
     deduct
    -0.67
     ashore
    -0.65
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    CHO
    -0.62
    ATIVE
    -0.60
     nonex
    -0.59
     weary
    -0.58
     CODE
    -0.58
     adolesc
    -0.57
     internally
    -0.57
    POSITIVE LOGITS
    erent
    1.24
    ees
    1.22
    ord
    1.19
    orts
    1.14
    ords
    1.13
    enegger
    1.09
    rey
    1.08
    ington
    1.08
    ield
    1.07
    inition
    1.05
    Activations Density 0.047%

    No Known Activations