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

    Neuronpedia

    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. 1755
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, "Valley."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Valley," particularly in a context related to Silicon Valley

    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
    sheet
    -0.70
     directive
    -0.62
     exorc
    -0.60
    dk
    -0.60
     df
    -0.59
     [+
    -0.59
    icking
    -0.58
    respons
    -0.58
     repr
    -0.57
     modules
    -0.56
    POSITIVE LOGITS
     Valley
    4.10
     valley
    2.57
     valleys
    1.57
     River
    1.54
     Mountain
    1.45
     Basin
    1.45
     Hills
    1.43
     Canyon
    1.40
    vale
    1.33
     Peninsula
    1.29
    Activations Density 0.019%

    No Known Activations