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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16
    Prev
    Next
    INDEX
    Explanations

    keywords related to the country "Burma" or "Myanmar"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "Bur."

    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
     Europa
    -0.67
     Integrity
    -0.64
     modesty
    -0.62
     Gleaming
    -0.58
    dfx
    -0.57
     corpor
    -0.57
     enhancement
    -0.57
     flourish
    -0.56
     CoC
    -0.56
     Patron
    -0.56
    POSITIVE LOGITS
    rito
    1.30
    rows
    1.27
    geoning
    1.25
    lington
    1.20
    leigh
    1.19
    zynski
    1.15
    rough
    1.12
    rill
    1.10
    rowing
    1.08
    row
    1.08
    Activations Density 0.016%

    No Known Activations