© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10695
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to things that are difficult or challenging

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "imp" and its variations, indicating a focus on the concept of "impact."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -1.07
    mate
    -0.72
    mates
    -0.70
    krit
    -0.68
     quo
    -0.67
    mberg
    -0.67
    gian
    -0.66
    çĦ
    -0.64
    taboola
    -0.62
     corrid
    -0.61
    POSITIVE LOGITS
    ossible
    1.46
    ulse
    1.45
    ressive
    1.40
    ression
    1.40
    ossibility
    1.34
    ractical
    1.31
    acts
    1.23
    romptu
    1.23
    regn
    1.20
    ressed
    1.14
    Activations Density 0.029%

    No Known Activations