© 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. 10-RES-JB
    11. 13848
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of academic degrees (e.g., PhD, MD)

    oai_token-act-pair · gpt-3.5-turbo

    academic degrees and professional titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decency
    -0.68
    advertising
    -0.68
    pload
    -0.65
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
    taboola
    -0.63
     dollar
    -0.62
     tariffs
    -0.62
     clauses
    -0.61
     fruits
    -0.59
    addons
    -0.59
    POSITIVE LOGITS
     PhD
    0.97
    .,
    0.94
     MPH
    0.93
     Candidate
    0.93
    VM
    0.82
    ociate
    0.81
    rint
    0.81
    sych
    0.77
    inical
    0.77
     Associate
    0.76
    Activations Density 0.034%

    No Known Activations