© 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. 0-RES-JB
    11. 8239
    Prev
    Next
    INDEX
    Explanations

    mentions of faculty members

    oai_token-act-pair · gpt-3.5-turbo

    references to faculty members and their roles within educational institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hots
    -0.67
    hero
    -0.65
     Tracker
    -0.65
    BACK
    -0.64
    é»Ĵ
    -0.64
    olation
    -0.61
    HER
    -0.60
    ãĥİ
    -0.60
     Zig
    -0.59
    Hero
    -0.59
    POSITIVE LOGITS
     faculty
    3.83
     Faculty
    2.65
     professors
    2.17
     faculties
    2.12
     alumni
    1.75
     teachers
    1.62
     campus
    1.55
     educators
    1.51
     adjunct
    1.49
    umni
    1.48
    Activations Density 0.019%

    No Known Activations