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. 5-RES-JB
    6. 2025
    Prev
    Next
    INDEX
    Explanations

    name entities related to research centers or institutes

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and institutions related to social and scientific issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     breeze
    -0.69
    milo
    -0.68
     quo
    -0.68
    auntlet
    -0.65
     suffice
    -0.64
    iesta
    -0.63
     sergeant
    -0.63
    isSpecialOrderable
    -0.63
     tram
    -0.63
     ashore
    -0.63
    POSITIVE LOGITS
     Computing
    0.88
     Disorders
    0.84
     Responsibility
    0.83
     Relations
    0.83
     Affairs
    0.83
     Studies
    0.83
     Protection
    0.82
     Preservation
    0.80
     Reconstruction
    0.78
     Psychology
    0.77
    Activations Density 0.219%

    No Known Activations