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. 431
    Prev
    Next
    INDEX
    Explanations

    dates or time-related phrases such as "Every [time unit]"

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases indicating frequency or regular occurrence

    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
    olas
    -0.86
    Ú
    -0.66
    arthy
    -0.65
    ainment
    -0.64
    raits
    -0.61
    onduct
    -0.60
    folios
    -0.60
    estyles
    -0.60
    agles
    -0.59
    dict
    -0.59
    POSITIVE LOGITS
    where
    1.32
    body
    1.17
    THING
    1.16
    time
    1.08
    day
    1.05
     year
    0.99
     ounce
    0.95
     time
    0.93
     conceivable
    0.90
     weekday
    0.90
    Activations Density 0.050%

    No Known Activations