© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 20207
    Prev
    Next
    INDEX
    Explanations

    days of the week combined with the time of day

    oai_token-act-pair · gpt-3.5-turbo

    specific days of the week and times referenced in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbuds
    -0.70
    ingen
    -0.67
     Reson
    -0.66
     univers
    -0.63
     behav
    -0.63
     Fabric
    -0.62
    =-=-=-=-=-=-=-=-
    -0.62
    abilia
    -0.60
    é¾įå
    -0.58
    åĬ
    -0.58
    POSITIVE LOGITS
     morning
    1.17
     mornings
    0.86
    morning
    0.85
     afternoon
    0.83
    noon
    0.78
    steen
    0.78
     evening
    0.74
     EDT
    0.72
    imester
    0.70
    hooting
    0.69
    Activations Density 0.099%

    No Known Activations