© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10235
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations, especially related to the Bay Area

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Bay Area

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

    No Comments

    Negative Logits
    etsk
    -0.98
    vous
    -0.86
    soDeliveryDate
    -0.82
    wcsstore
    -0.78
    ansson
    -0.73
    atem
    -0.73
    actionDate
    -0.72
    racuse
    -0.72
    email
    -0.72
    eur
    -0.72
    POSITIVE LOGITS
     Area
    1.00
     Rapid
    0.91
     Peninsula
    0.84
     Arcade
    0.80
     Regional
    0.78
     Circuit
    0.76
     Gins
    0.74
     Development
    0.73
     Specific
    0.73
     Authority
    0.73
    Activations Density 0.010%

    No Known Activations