© 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. 12101
    Prev
    Next
    INDEX
    Explanations

    locations or places mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of geographical locations mentioned in relation to activities or events

    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
    catentry
    -0.76
    ibe
    -0.71
    cum
    -0.71
    fml
    -0.69
    govtrack
    -0.68
    DragonMagazine
    -0.66
    uitous
    -0.65
    EStreamFrame
    -0.64
    tg
    -0.64
    empt
    -0.64
    POSITIVE LOGITS
     dozens
    1.43
     numerous
    1.27
     thirteen
    1.27
     seventeen
    1.26
     fourteen
    1.25
     hundreds
    1.25
     eleven
    1.25
     nine
    1.24
     several
    1.24
     countless
    1.23
    Activations Density 0.614%

    No Known Activations