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. 2345
    Prev
    Next
    INDEX
    Explanations

    words related to roundness, whether physical or metaphorical

    oai_token-act-pair · gpt-3.5-turbo

    terms related to rounding and rounded shapes or concepts

    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
    ettel
    -0.78
    natureconservancy
    -0.77
     lender
    -0.70
    ufact
    -0.70
    orship
    -0.69
     conditioning
    -0.66
    alogy
    -0.64
     appropriation
    -0.62
    acca
    -0.62
    iments
    -0.62
    POSITIVE LOGITS
    abouts
    1.05
     Seym
    0.96
     corners
    0.92
    about
    0.91
    table
    0.87
    bottom
    0.82
    Rect
    0.80
    trip
    0.78
    ij士
    0.75
    oslav
    0.75
    Activations Density 0.022%

    No Known Activations