© 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. 9-RES-JB
    11. 11170
    Prev
    Next
    INDEX
    Explanations

    events related to first public appearances or first games

    oai_token-act-pair · gpt-3.5-turbo

    references to first-time or significant appearances and performances in sports or public events

    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
    Not in Any Lists

    No Comments

    Negative Logits
     abound
    -0.89
    inguishable
    -0.76
    bara
    -0.71
    ubes
    -0.69
    isson
    -0.69
    ruciating
    -0.61
    aples
    -0.58
     continuum
    -0.57
    conservancy
    -0.57
    aintain
    -0.57
    POSITIVE LOGITS
     EVER
    1.08
     appearance
    0.93
     ever
    0.91
     outing
    0.88
     foray
    0.86
     anniversary
    0.83
     VIDEOS
    0.82
    Ever
    0.79
    ONY
    0.78
     Appearance
    0.75
    Activations Density 0.241%

    No Known Activations