© 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. 10-RES-JB
    11. 5465
    Prev
    Next
    INDEX
    Explanations

    phrases related to showcasing or demonstrating support or actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "show" in various contexts

    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
    etheless
    -0.72
     Blackwell
    -0.67
    kson
    -0.66
    ignty
    -0.63
     Clockwork
    -0.63
    ADE
    -0.62
    ataka
    -0.61
    ately
    -0.61
    illet
    -0.60
    tymology
    -0.59
    POSITIVE LOGITS
    biz
    1.54
    case
    1.34
    cases
    1.28
    downs
    1.27
    alter
    1.21
    manship
    1.17
    room
    1.10
    rooms
    1.10
    tek
    1.04
    boat
    1.03
    Activations Density 0.047%

    No Known Activations