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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 12083
    Prev
    Next
    INDEX
    Explanations

    dates, especially those associated with events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to the day "Tuesday"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ript
    -0.89
    abet
    -0.87
    onductor
    -0.87
    ordes
    -0.84
    luster
    -0.82
    onso
    -0.77
    ategory
    -0.76
    onse
    -0.73
    pire
    -0.72
    ris
    -0.72
    POSITIVE LOGITS
     morning
    1.51
     afternoon
    1.43
     night
    1.39
     evening
    1.36
     mornings
    1.22
    morning
    1.08
     nights
    1.07
     Night
    1.06
     evenings
    1.03
     Morning
    0.94
    Activations Density 0.030%

    No Known Activations