© 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. 11-RES-JB
    11. 7722
    Prev
    Next
    INDEX
    Explanations

    keywords related to hiring or consulting

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate hiring or employment actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -1.03
     forgetting
    -0.86
    ific
    -0.79
    rained
    -0.77
    abiding
    -0.75
     doesnt
    -0.74
    raped
    -0.71
    forcing
    -0.70
    living
    -0.69
     didnt
    -0.69
    POSITIVE LOGITS
     oversee
    1.47
     analyze
    1.36
     investigate
    1.27
     develop
    1.25
     administer
    1.24
     coordinate
    1.24
     evaluate
    1.22
     advise
    1.21
     assist
    1.21
     study
    1.21
    Activations Density 0.179%

    No Known Activations