Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 22383
    Prev
    Next
    INDEX
    Explanations

    words related to geometric shapes, specifically triangles

    oai_token-act-pair · gpt-3.5-turbo

    references to triangles

    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
    giving
    -0.79
    VO
    -0.77
    assetsadobe
    -0.74
    ICH
    -0.74
    taking
    -0.73
    BuyableInstoreAndOnline
    -0.72
    tv
    -0.72
    nings
    -0.72
    VICE
    -0.70
    audi
    -0.70
    POSITIVE LOGITS
     triangle
    0.93
     Triangle
    0.87
     shaped
    0.79
    ModLoader
    0.77
    adoes
    0.77
    hedral
    0.74
     triangles
    0.72
     Rect
    0.71
    ilogy
    0.69
    ropy
    0.69
    Activations Density 0.025%

    No Known Activations