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

    Neuronpedia

    Jacobian LensNEW
    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. 1816
    Prev
    Next
    INDEX
    Explanations

    regions, states, and countries

    oai_token-act-pair · gpt-3.5-turbo

    specific geographic locations and demographic information

    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
     meanings
    -0.73
     consensual
    -0.67
    minist
    -0.60
     privileges
    -0.60
    agonist
    -0.57
    models
    -0.57
    iple
    -0.56
    ivities
    -0.55
     ways
    -0.55
    products
    -0.55
    POSITIVE LOGITS
    Cong
    0.66
    ague
    0.64
    itto
    0.62
    avia
    0.61
    boa
    0.60
    SEA
    0.60
    ataka
    0.60
    Chart
    0.60
     fared
    0.59
    okia
    0.59
    Activations Density 0.255%

    No Known Activations