© 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. 23863
    Prev
    Next
    INDEX
    Explanations

    names of geographical areas, specifically "Bay Area"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bay Area

    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
    terday
    -0.75
    matter
    -0.74
     Beir
    -0.72
    iferation
    -0.69
     Painter
    -0.67
     Luthor
    -0.63
    zzle
    -0.62
    ×ķ
    -0.62
    isers
    -0.60
    utive
    -0.59
    POSITIVE LOGITS
    onet
    1.36
    esian
    1.32
    ou
    1.08
     Area
    0.90
    onne
    0.88
    front
    0.87
    nard
    0.81
    rina
    0.81
    ucc
    0.80
    liner
    0.80
    Activations Density 0.028%

    No Known Activations