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. 8773
    Prev
    Next
    INDEX
    Explanations

    numerical references to anniversaries or milestones

    oai_token-act-pair · gpt-3.5-turbo

    ordinal numbers indicating anniversaries or significant milestones

    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
    anamo
    -0.76
    bows
    -0.74
    bos
    -0.72
    bring
    -0.72
    raltar
    -0.69
    roth
    -0.69
    recy
    -0.69
    chool
    -0.68
    skirts
    -0.67
    ateral
    -0.67
    POSITIVE LOGITS
     anniversary
    1.39
     Anniversary
    1.34
     percentile
    1.19
     birthday
    1.12
    ousand
    1.10
     Annual
    1.07
     installment
    1.02
     Birthday
    0.99
     edition
    0.93
     Dalai
    0.90
    Activations Density 0.040%

    No Known Activations