© 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. 8-RES-JB
    11. 11361
    Prev
    Next
    INDEX
    Explanations

    phrases related to people working in different professions or job positions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of employment or job-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emonic
    -0.75
     constitu
    -0.74
    xual
    -0.68
    angular
    -0.66
    ylon
    -0.65
     Bubble
    -0.65
     Augustus
    -0.65
    ople
    -0.64
    ĪĴ
    -0.64
    anus
    -0.64
    POSITIVE LOGITS
     tirelessly
    1.07
     ethic
    1.02
    hops
    1.00
     diligently
    0.98
     overtime
    0.94
     collabor
    0.92
    bench
    0.92
    paces
    0.85
    forces
    0.84
    aday
    0.84
    Activations Density 0.076%

    No Known Activations