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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 18302
    Prev
    Next
    INDEX
    Explanations

    measurements related to the physical size of objects

    oai_token-act-pair · gpt-3.5-turbo

    measurements of dimensions and sizes

    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
    States
    -0.75
    YN
    -0.75
    Tea
    -0.71
    çͰ
    -0.67
    imaru
    -0.67
    tag
    -0.65
    uld
    -0.65
    969
    -0.63
    Mail
    -0.62
    Drug
    -0.62
    POSITIVE LOGITS
     diameter
    0.96
     apiece
    0.88
     circumference
    0.87
     (~
    0.87
    iameter
    0.87
     radius
    0.79
     horizontally
    0.76
    ipes
    0.74
    itude
    0.73
     each
    0.72
    Activations Density 0.065%

    No Known Activations