© 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. 19428
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizational entities, likely acronyms such as "AF" and "SC."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific organization or acronym related to armed forces

    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
    igators
    -0.75
    ozo
    -0.74
     Boone
    -0.72
    Accessory
    -0.72
    essee
    -0.71
    oses
    -0.61
     Vaugh
    -0.61
    agate
    -0.59
     Blackwell
    -0.59
     Sapphire
    -0.59
    POSITIVE LOGITS
    RIC
    1.05
    ornia
    0.96
    SPA
    0.92
    FL
    0.88
    RA
    0.85
    lesh
    0.83
    ghan
    0.82
    tering
    0.81
    riend
    0.80
    rica
    0.80
    Activations Density 0.038%

    No Known Activations