© 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. 0-RES-JB
    11. 13249
    Prev
    Next
    INDEX
    Explanations

    mentions of locally produced goods or services

    oai_token-act-pair · gpt-3.5-turbo

    references to local products or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wonderland
    -0.79
     Eur
    -0.64
     Inquis
    -0.64
     Customs
    -0.63
     Gest
    -0.63
     Material
    -0.63
    chwitz
    -0.62
     Arbit
    -0.61
     Illuminati
    -0.61
    [/
    -0.59
    POSITIVE LOGITS
     locally
    2.55
     statewide
    1.45
     slate
    1.22
    oqu
    1.13
     mild
    1.04
     municip
    0.99
    nesota
    0.87
     localized
    0.87
    bernatorial
    0.87
     runoff
    0.85
    Activations Density 0.022%

    No Known Activations