Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 307
    Prev
    Next
    INDEX
    Explanations

    dates and time-related information

    oai_token-act-pair · gpt-3.5-turbo

    references to timekeeping systems and calendars

    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
    workshop
    -0.74
    grow
    -0.72
    athing
    -0.72
    Priv
    -0.71
    ilage
    -0.68
    mob
    -0.68
     Flavoring
    -0.67
    bags
    -0.67
    reau
    -0.67
    Asset
    -0.67
    POSITIVE LOGITS
     clocks
    1.51
     calendar
    1.45
     Calendar
    1.44
     clock
    1.40
     Daylight
    1.39
     UTC
    1.39
     calendars
    1.37
     GMT
    1.34
    GMT
    1.33
    UTC
    1.32
    Activations Density 0.476%

    No Known Activations