© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23030
    Prev
    Next
    INDEX
    Explanations

    words related to riddles and enigmas

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "und."

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.63
     apiece
    -0.62
     wider
    -0.60
     losers
    -0.60
     majors
    -0.59
    fig
    -0.58
    ======
    -0.58
     speakers
    -0.58
     MPG
    -0.58
     outwe
    -0.58
    POSITIVE LOGITS
    rums
    1.10
    erest
    1.07
    ecided
    1.04
    ocumented
    1.03
    erers
    1.03
    emonium
    1.02
    erella
    1.02
    erer
    1.01
    efined
    0.97
    reth
    0.96
    Activations Density 0.035%

    No Known Activations