© 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. 9-RES-JB
    11. 1947
    Prev
    Next
    INDEX
    Explanations

    the word "all" preceded by various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •All the Features!

    No Comments

    Negative Logits
     Kamp
    -0.70
    assembly
    -0.62
    gee
    -0.60
    SHIP
    -0.59
    inth
    -0.56
     Viz
    -0.55
    illy
    -0.54
     cutter
    -0.54
     anywhere
    -0.54
     Caption
    -0.53
    POSITIVE LOGITS
     sorts
    1.23
     kinds
    1.20
    igators
    1.10
    usions
    1.06
    ocating
    1.00
    iances
    0.99
    edged
    0.98
    things
    0.96
    udes
    0.95
    igator
    0.93
    Activations Density 0.121%

    No Known Activations