© 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. 10-RES-JB
    11. 3060
    Prev
    Next
    INDEX
    Explanations

    mentions of dates and times

    oai_token-act-pair · gpt-3.5-turbo

    terms related to timing or temporal references in events

    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
    ography
    -0.63
    ories
    -0.62
    esome
    -0.59
    Reviewer
    -0.59
    ittal
    -0.57
     Rings
    -0.57
    ographical
    -0.57
     Offic
    -0.55
     brim
    -0.54
    ophe
    -0.53
    POSITIVE LOGITS
     Tuesday
    1.24
     Wednesday
    1.24
     Thursday
    1.22
     Monday
    1.22
     Friday
    1.20
     Saturday
    1.12
     Sunday
    1.07
     yesterday
    1.05
     afternoon
    1.05
    Monday
    0.99
    Activations Density 0.053%

    No Known Activations