© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    positions or titles of authority, such as police officer or chief financial officer

    oai_token-act-pair · gpt-3.5-turbo

    titles and roles associated with various leadership and officer positions

    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
     Wonderland
    -0.73
     tsunami
    -0.64
     wildfires
    -0.58
    adoes
    -0.58
     tsun
    -0.58
     Haiti
    -0.56
     contag
    -0.56
     Pengu
    -0.56
     Tears
    -0.55
     Firefly
    -0.54
    POSITIVE LOGITS
    imester
    0.85
    artment
    0.80
     officer
    0.80
    endment
    0.78
    wark
    0.78
    incial
    0.76
    ourse
    0.71
    ciplinary
    0.70
    ceptor
    0.70
     adviser
    0.70
    Activations Density 0.433%

    No Known Activations