© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 4411
    Prev
    Next
    INDEX
    Explanations

    information about various professionals and their roles or titles

    oai_token-act-pair · gpt-3.5-turbo

    occupational roles and professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ouls
    -0.78
    ciating
    -0.78
    onies
    -0.75
    cific
    -0.75
    tone
    -0.73
    nces
    -0.73
    iments
    -0.72
     Zup
    -0.71
    ory
    -0.71
    ciation
    -0.69
    POSITIVE LOGITS
     educator
    1.22
     lecturer
    1.07
     philosopher
    1.01
     entrepreneur
    1.00
     musician
    0.99
     blogger
    0.99
     businessman
    0.96
     poet
    0.95
     translator
    0.93
     thinker
    0.93
    Activations Density 0.191%

    No Known Activations