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. 19948
    Prev
    Next
    INDEX
    Explanations

    names of people, historical events, and political terms

    oai_token-act-pair · gpt-3.5-turbo

    historical figures and events related to governance and military actions

    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
     Xiaomi
    -0.95
    ï¸ı
    -0.86
    Uber
    -0.85
     Snapchat
    -0.83
    andowski
    -0.83
    VPN
    -0.83
     esports
    -0.79
     emoji
    -0.79
     veggies
    -0.79
     wellness
    -0.77
    POSITIVE LOGITS
     postwar
    1.12
     1936
    1.08
     1912
    1.07
     1914
    1.07
    oslov
    1.06
     1939
    1.04
     1909
    1.04
     1932
    1.03
     1938
    1.03
     1946
    1.01
    Activations Density 1.764%

    No Known Activations