© 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. 6-RES-JB
    11. 14461
    Prev
    Next
    INDEX
    Explanations

    words related to work and workplace settings

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ukrain
    -0.91
     Flavoring
    -0.77
     Russo
    -0.69
    EStream
    -0.69
     Bol
    -0.69
     constitu
    -0.68
    ĪĴ
    -0.66
    olic
    -0.66
    wcs
    -0.65
    pha
    -0.64
    POSITIVE LOGITS
     ethic
    1.18
    aday
    1.11
    station
    1.09
    bench
    1.04
    manship
    1.03
    day
    0.98
    week
    0.98
    wear
    0.92
    hour
    0.90
    days
    0.88
    Activations Density 0.065%

    No Known Activations