© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 11168
    Prev
    Next
    INDEX
    Explanations

    mentions of weekends

    oai_token-act-pair · gpt-3.5-turbo

    references to "weekend."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abet
    -0.86
    ifice
    -0.78
    atem
    -0.74
    cro
    -0.74
    inf
    -0.73
    onne
    -0.72
    rate
    -0.72
    lez
    -0.72
     cf
    -0.71
    pres
    -0.71
    POSITIVE LOGITS
     mornings
    1.28
     weekend
    1.21
     afternoon
    1.20
     nights
    1.14
     morning
    1.09
     weekends
    1.09
     evenings
    1.03
     evening
    1.02
     night
    0.97
     brunch
    0.92
    Activations Density 0.012%

    No Known Activations