© 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 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. 9-RES-JB
    11. 1984
    Prev
    Next
    INDEX
    Explanations

    words related to work and workplace environments

    oai_token-act-pair · gpt-3.5-turbo

    references to work or the act of working in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ukrain
    -0.99
    olic
    -0.72
     constitu
    -0.69
     Canaver
    -0.67
    uyomi
    -0.67
     Axis
    -0.63
    adoes
    -0.62
     Adin
    -0.62
    emonic
    -0.61
     Fernand
    -0.61
    POSITIVE LOGITS
    aday
    1.24
    days
    1.15
    day
    1.08
    station
    1.00
    hour
    0.99
    bench
    0.98
    lifting
    0.98
     ethic
    0.97
    night
    0.94
    manship
    0.92
    Activations Density 0.056%

    No Known Activations