© 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. 10-RES-JB
    11. 13964
    Prev
    Next
    INDEX
    Explanations

    phrases related to the scope of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "scope" in various contexts

    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
    ublic
    -0.67
    ocard
    -0.60
    pron
    -0.59
    ãģį
    -0.59
    ston
    -0.59
    eah
    -0.59
    odge
    -0.59
    é¾įå
    -0.58
     Frankenstein
    -0.57
    ASY
    -0.57
    POSITIVE LOGITS
     scope
    1.03
     creep
    0.90
     magnification
    0.87
     Scope
    0.85
    izons
    0.83
    ifi
    0.78
    Scope
    0.77
     radius
    0.75
    illary
    0.75
    emouth
    0.75
    Activations Density 0.035%

    No Known Activations