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. 11-RES-JB
    6. 7356
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning specific states in the United States

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific states and their unique legal or social standings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ovan
    -0.73
     Spectre
    -0.73
    worms
    -0.73
     ali
    -0.71
    ÄŁ
    -0.68
    BBC
    -0.68
     Rwanda
    -0.68
    shop
    -0.67
     Inquisition
    -0.67
    RT
    -0.65
    POSITIVE LOGITS
     Midwest
    1.45
     states
    1.36
     Appalach
    1.25
     Northeast
    1.24
     nation
    1.20
     state
    1.20
    States
    1.18
     Appalachian
    1.15
     contiguous
    1.11
     statewide
    1.10
    Activations Density 0.285%

    No Known Activations