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. 10-RES-JB
    6. 23819
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations, specifically those containing the term "East."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "East."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ATURE
    -0.75
    awaru
    -0.70
    vous
    -0.69
    utical
    -0.66
     refunds
    -0.65
     inherit
    -0.65
    acet
    -0.64
    INAL
    -0.63
    essed
    -0.63
    hement
    -0.62
    POSITIVE LOGITS
     Coast
    1.06
    side
    0.98
    bourne
    0.97
     coast
    0.97
    lake
    0.94
     Midlands
    0.93
    enders
    0.93
    leigh
    0.93
    ward
    0.92
    bound
    0.92
    Activations Density 0.023%

    No Known Activations