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. 3-RES-JB
    6. 10243
    Prev
    Next
    INDEX
    Explanations

    locations or events related to Tel Aviv

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Tel Aviv and related geographical entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pyth
    -0.78
     dysph
    -0.69
     pestic
    -0.65
    perature
    -0.65
     Reynolds
    -0.63
     clot
    -0.62
     reconc
    -0.62
     Appalachian
    -0.61
    ptic
    -0.61
    awaru
    -0.61
    POSITIVE LOGITS
     Aviv
    1.25
    anyahu
    0.97
    ites
    0.92
     Netanyahu
    0.92
     Juda
    0.86
     ×
    0.86
     Torah
    0.79
     Pact
    0.75
    ite
    0.74
    aretz
    0.74
    Activations Density 0.011%

    No Known Activations