© 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. 9391
    Prev
    Next
    INDEX
    Explanations

    proper nouns/ names or phrases related to law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    words related to identity or naming conventions

    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
    erial
    -0.66
    wcs
    -0.66
     EDITION
    -0.62
    ĭ
    -0.59
    ORK
    -0.58
     SUPER
    -0.58
    lance
    -0.58
    ãĥ£
    -0.57
    higher
    -0.57
    Object
    -0.55
    POSITIVE LOGITS
     himself
    1.03
    's
    1.00
     herself
    0.88
     recalls
    0.87
     admits
    0.83
     remembers
    0.83
    enegger
    0.82
     recounts
    0.77
     admitted
    0.77
     Productions
    0.76
    Activations Density 0.191%

    No Known Activations