© 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 EvalsExportsAPI 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. 18214
    Prev
    Next
    INDEX
    Explanations

    words related to product launches or announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to the launch of new products or initiatives

    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
     defeats
    -0.74
     pse
    -0.74
     notor
    -0.74
    :]
    -0.73
    earchers
    -0.72
    !]
    -0.72
     ordinarily
    -0.71
    quickShipAvailable
    -0.71
    .}
    -0.71
    ;;;;;;;;
    -0.70
    POSITIVE LOGITS
     prototype
    0.77
     portfolio
    0.75
     Corridor
    0.74
     pipeline
    0.74
     Gateway
    0.72
     roadmap
    0.69
     Bridge
    0.68
     Cannabis
    0.68
    Rail
    0.67
     Telescope
    0.67
    Activations Density 0.732%

    No Known Activations