© 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. 5115
    Prev
    Next
    INDEX
    Explanations

    names related to particular places, like "Shaw", "Finch", and "Chow"

    oai_token-act-pair · gpt-3.5-turbo

    names of people, specifically those with the last name "Shaw."

    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
    afort
    -0.89
    ocaust
    -0.86
    omez
    -0.76
    orically
    -0.74
    ographically
    -0.70
    ochemical
    -0.69
    vironment
    -0.69
    ographical
    -0.68
    ocaly
    -0.67
    ocent
    -0.66
    POSITIVE LOGITS
    kat
    1.10
    cross
    0.98
    arma
    0.97
    yer
    0.94
    blade
    0.90
    geon
    0.85
    mere
    0.83
    aii
    0.82
    bones
    0.81
    bone
    0.80
    Activations Density 0.038%

    No Known Activations