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. 4461
    Prev
    Next
    INDEX
    Explanations

    words related to the United States or its institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to the United States

    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
     STATS
    -0.68
    theless
    -0.66
     hairs
    -0.58
     simmer
    -0.58
    adobe
    -0.57
     foreseeable
    -0.57
     ker
    -0.57
     unpre
    -0.56
     organising
    -0.56
     KP
    -0.56
    POSITIVE LOGITS
    .,
    1.46
    .?
    1.24
    .;
    1.14
    .:
    1.13
    .—
    1.06
    .,"
    1.06
    .-
    1.04
    .$
    1.04
    ./
    1.00
    .–
    0.93
    Activations Density 0.049%

    No Known Activations