© 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. 12-RES-JB
    11. 4315
    Prev
    Next
    INDEX
    Explanations

    biographical information about sports figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to successful sports teams and their achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    enza
    -0.98
    catentry
    -0.83
    thia
    -0.83
     skelet
    -0.83
    Catal
    -0.79
    rylic
    -0.78
    AU
    -0.76
    ctica
    -0.76
     Cosponsors
    -0.74
    aida
    -0.72
    POSITIVE LOGITS
     NFC
    1.73
     AFC
    1.59
     Packers
    1.28
     Super
    1.27
     Week
    1.22
     DV
    1.20
     Patriots
    1.20
     Seahawks
    1.19
     Colts
    1.17
     Peyton
    1.16
    Activations Density 0.352%

    No Known Activations