© 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. 20801
    Prev
    Next
    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating dates and significant 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
    forts
    -0.76
    ideos
    -0.76
     disse
    -0.64
    bda
    -0.63
     implements
    -0.63
    irez
    -0.63
    interface
    -0.62
    anse
    -0.62
     circulate
    -0.61
    artments
    -0.61
    POSITIVE LOGITS
     shaping
    1.07
     Election
    0.81
     Halloween
    0.79
     Celebration
    0.74
     supposed
    0.73
     Candle
    0.72
     ripe
    0.70
     Boxing
    0.70
     Memorial
    0.70
    iversary
    0.70
    Activations Density 0.102%

    No Known Activations