© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 2838
    Prev
    Next
    INDEX
    Explanations

    phrases related to the state of Idaho

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Idaho and related locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ively
    -0.82
    iveness
    -0.80
    xual
    -0.76
    manship
    -0.75
    isks
    -0.73
    eed
    -0.73
    thood
    -0.71
    ister
    -0.71
    es
    -0.70
    isters
    -0.68
    POSITIVE LOGITS
     Falls
    1.13
     Idaho
    0.97
     Grizzlies
    0.91
    anooga
    0.82
     Montana
    0.81
     Boise
    0.80
     Anchorage
    0.79
    REM
    0.76
     Potato
    0.76
    EStream
    0.73
    Activations Density 0.073%

    No Known Activations