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. 3-RES-JB
    6. 14541
    Prev
    Next
    INDEX
    Explanations

    numeric age references in hyphenated format

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.82
     Scrib
    -0.79
    Ń·
    -0.77
     pens
    -0.76
    achus
    -0.73
    ulhu
    -0.67
    erella
    -0.67
     Dickinson
    -0.65
     Cassidy
    -0.65
     naughty
    -0.64
    POSITIVE LOGITS
    sized
    1.11
    interstitial
    0.95
    degree
    0.94
    based
    0.94
    themed
    0.90
    generation
    0.90
    length
    0.90
    years
    0.89
    times
    0.89
    appointed
    0.86
    Activations Density 0.152%

    No Known Activations