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. 8-RES-JB
    6. 18912
    Prev
    Next
    INDEX
    Explanations

    dates and months mentioned in documents

    oai_token-act-pair · gpt-3.5-turbo

    references to specific months

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haram
    -0.85
    otle
    -0.77
    anooga
    -0.74
    aque
    -0.73
    ioch
    -0.71
    enh
    -0.69
    oos
    -0.69
    emort
    -0.69
    leck
    -0.68
    gers
    -0.68
    POSITIVE LOGITS
    ths
    0.85
    pring
    0.81
     Ukrain
    0.81
     Ples
    0.80
    nd
    0.75
    flower
    0.75
    itime
    0.71
    theless
    0.71
    iversary
    0.71
    rences
    0.70
    Activations Density 0.068%

    No Known Activations