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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 213
    Prev
    Next
    INDEX
    Explanations

    dates expressed in relative terms (e.g., "three years ago") or in specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    temporal markers and phrases that indicate timing or sequencing of 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
     goddamn
    -0.90
     darn
    -0.84
     extraord
    -0.82
    âĢķ
    -0.80
     damn
    -0.78
     ðŁĻĤ
    -0.78
     damned
    -0.76
     ALWAYS
    -0.76
     EVERY
    -0.76
     godd
    -0.73
    POSITIVE LOGITS
    resa
    0.99
    odore
    0.90
    iday
    0.89
     spokeswoman
    0.88
    rovers
    0.87
     Wednesday
    0.85
    nsic
    0.85
     Thursday
    0.84
    onding
    0.83
     spokesman
    0.83
    Activations Density 0.270%

    No Known Activations