© 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. 1-RES-JB
    11. 14203
    Prev
    Next
    INDEX
    Explanations

    phrases related to being laid off or dismissed from a job

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "off."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Emir
    -0.67
     liter
    -0.64
     organize
    -0.62
     cm
    -0.61
    ¿½
    -0.61
     tremend
    -0.61
     Theft
    -0.59
     Occupations
    -0.58
    %]
    -0.58
     Id
    -0.57
    POSITIVE LOGITS
    off
    0.99
    ment
    0.89
    ments
    0.89
    ansas
    0.85
    enders
    0.81
    ishly
    0.81
    ices
    0.80
    shore
    0.79
    anza
    0.78
    stairs
    0.77
    Activations Density 0.010%

    No Known Activations