© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 10293
    Prev
    Next
    INDEX
    Explanations

    specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific days of the week

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

    No Comments

    Negative Logits
     Orche
    -0.67
    webkit
    -0.66
     Compos
    -0.66
     Controls
    -0.65
    ership
    -0.62
    tymology
    -0.61
     Explan
    -0.61
    itect
    -0.61
     specifications
    -0.59
    arily
    -0.59
    POSITIVE LOGITS
     afternoon
    1.07
    nesday
    0.99
     mornings
    0.96
     morning
    0.88
     night
    0.81
    Morning
    0.80
     evening
    0.80
     nights
    0.79
    days
    0.78
     evenings
    0.75
    Activations Density 0.043%

    No Known Activations