© 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. 4-RES-JB
    11. 20920
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations with the word "Creek"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific creek names

    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
    berman
    -0.78
     mathemat
    -0.76
     livest
    -0.75
    Downloadha
    -0.74
    =-=-=-=-=-=-=-=-
    -0.69
    oppable
    -0.68
     streng
    -0.67
     newsp
    -0.66
    neapolis
    -0.66
    atem
    -0.64
    POSITIVE LOGITS
    dale
    1.15
     Creek
    1.09
     Meadows
    0.92
     Canyon
    0.91
     Falls
    0.90
     Valley
    0.88
    weed
    0.87
    wood
    0.85
     Trail
    0.83
     valley
    0.83
    Activations Density 0.011%

    No Known Activations