Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10982
    Prev
    Next
    INDEX
    Explanations

    geographical locations, specifically cities and universities

    oai_token-act-pair · gpt-3.5-turbo

    names of specific locations and terms related to immigration and refugee issues

    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
     Cu
    -0.73
    buster
    -0.68
     hij
    -0.64
    iling
    -0.63
     telev
    -0.62
     Detective
    -0.62
     conglomer
    -0.61
     filler
    -0.61
    ijn
    -0.60
     Lau
    -0.60
    POSITIVE LOGITS
    throp
    2.45
     Arbor
    2.25
     Refugees
    1.94
    kept
    1.23
     Kabul
    1.07
    ickr
    1.06
    uties
    1.04
    wcsstore
    1.02
    atche
    1.00
     humane
    0.96
    Activations Density 0.049%

    No Known Activations