© 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. 13237
    Prev
    Next
    INDEX
    Explanations

    historical records or achievements associated with specific entities like sports teams or countries

    oai_token-act-pair · gpt-3.5-turbo

    references to historical contexts and events related to sports and notable accomplishments

    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
    interstitial
    -0.72
    ittees
    -0.64
    ilaterally
    -0.61
    sol
    -0.56
     Situation
    -0.56
    sers
    -0.55
    avorable
    -0.54
    aways
    -0.54
    tones
    -0.53
    lees
    -0.53
    POSITIVE LOGITS
     history
    2.11
    history
    1.73
     History
    1.54
    History
    1.28
     histories
    1.20
     ann
    1.16
     lore
    1.09
    ISTORY
    1.03
     era
    1.02
     lifetime
    0.97
    Activations Density 0.155%

    No Known Activations