© 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. 9-RES-JB
    11. 3159
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to leadership or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to power dynamics and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raviolet
    -0.73
     Granger
    -0.68
    ierre
    -0.67
    ortium
    -0.63
     subp
    -0.63
    ertodd
    -0.61
     Fraser
    -0.61
     missing
    -0.60
    ãĥ¤
    -0.60
     Pascal
    -0.59
    POSITIVE LOGITS
     supreme
    1.04
    ghai
    0.82
    pin
    0.77
     peacefully
    0.74
    law
    0.74
    orship
    0.74
    warts
    0.73
    pins
    0.72
    lord
    0.72
    lords
    0.72
    Activations Density 0.102%

    No Known Activations