© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3046
    Prev
    Next
    INDEX
    Explanations

    various professional roles, such as officer, captain, president, or editor, within different contexts like law enforcement, sports, academia, and media

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    job titles and roles in various professional fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oks
    -0.77
     Beasts
    -0.71
    ouls
    -0.69
    hens
    -0.68
     Attacks
    -0.67
    ounds
    -0.65
    ppings
    -0.62
     Countries
    -0.62
    itars
    -0.61
     Blocks
    -0.60
    POSITIVE LOGITS
     instructor
    1.01
     advisor
    1.01
     apprentice
    0.98
     recru
    0.97
     assistant
    0.97
     adviser
    0.95
     specializing
    0.95
     firefighter
    0.95
     dancer
    0.93
     contestant
    0.93
    Activations Density 0.213%

    No Known Activations