© 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. 3-RES-JB
    11. 602
    Prev
    Next
    INDEX
    Explanations

    phrases related to workplace issues and actions

    oai_token-act-pair · gpt-3.5-turbo

    references to work and employment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.72
     Bour
    -0.72
     Ukrain
    -0.70
     constitu
    -0.70
    EStream
    -0.66
     Flavoring
    -0.65
    anamo
    -0.63
     Russo
    -0.60
     Vi
    -0.60
     Yen
    -0.60
    POSITIVE LOGITS
    bench
    1.34
    station
    1.18
     ethic
    1.14
    fare
    1.12
    aday
    1.11
    manship
    1.08
    horse
    1.07
    hops
    1.04
    flows
    1.00
    work
    0.98
    Activations Density 0.075%

    No Known Activations