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. 11-RES-JB
    6. 11057
    Prev
    Next
    INDEX
    Explanations

    measurements with a focus on millimeters and thickness

    oai_token-act-pair · gpt-3.5-turbo

    measurements and specifications related to millimeters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lez
    -0.91
    raise
    -0.79
    eve
    -0.77
    leased
    -0.76
    come
    -0.75
    oeuv
    -0.75
    Score
    -0.74
    eer
    -0.73
    pects
    -0.73
    analysis
    -0.73
    POSITIVE LOGITS
     diameter
    1.11
     thick
    0.98
     thickness
    0.90
     radiator
    0.83
     tall
    0.82
     focal
    0.81
     socket
    0.80
     lens
    0.78
     caliber
    0.76
     spacing
    0.76
    Activations Density 0.051%

    No Known Activations