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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 20749
    Prev
    Next
    INDEX
    Explanations

    mentions or references to the state of Maine

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Maine" and related references to the state

    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
    sem
    -0.83
    itual
    -0.81
    alez
    -0.79
    pter
    -0.78
    intern
    -0.78
    impl
    -0.77
    gio
    -0.72
    idious
    -0.72
    ×Ļ×
    -0.72
    byn
    -0.71
    POSITIVE LOGITS
     Maine
    0.88
     Madness
    0.80
     lobster
    0.80
     Chiefs
    0.79
     Ridge
    0.78
     Township
    0.78
     Residents
    0.77
     Coast
    0.76
     Lamp
    0.75
     Shore
    0.72
    Activations Density 0.008%

    No Known Activations