© 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. 3-RES-JB
    11. 4794
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    names of places or entities, specifically related to locations and organizations mentioned in the context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vich
    -0.91
    otle
    -0.87
    ception
    -0.85
    orge
    -0.83
    yond
    -0.76
    ingly
    -0.75
    achy
    -0.74
    DNA
    -0.74
    love
    -0.73
    oxic
    -0.73
    POSITIVE LOGITS
     FSA
    0.84
     eleph
    0.73
    Ĥª
    0.73
     Palestin
    0.73
    iless
    0.72
    rescent
    0.71
     Divide
    0.70
    dayName
    0.69
     staging
    0.68
    ruciating
    0.68
    Activations Density 0.020%

    No Known Activations