© 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. 3-RES-JB
    11. 9502
    Prev
    Next
    INDEX
    Explanations

    words related to the extent or boundaries of a concept or issue

    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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.69
    \":
    -0.67
    Pass
    -0.66
     Valentine
    -0.66
    ston
    -0.65
    Indust
    -0.63
    joining
    -0.62
    Beat
    -0.61
     pengu
    -0.61
    Mart
    -0.60
    POSITIVE LOGITS
     scope
    1.21
     Scope
    1.05
    illary
    0.86
    scope
    0.83
    Scope
    0.82
    ategory
    0.78
    mares
    0.78
    psons
    0.77
    emouth
    0.76
    opes
    0.75
    Activations Density 0.010%

    No Known Activations