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. 18202
    Prev
    Next
    INDEX
    Explanations

    mentions of 3D technology

    oai_token-act-pair · gpt-3.5-turbo

    references to 3D technology and its applications

    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
    kai
    -0.74
     Bulg
    -0.74
    akens
    -0.71
    ti
    -0.68
    udeb
    -0.67
    pid
    -0.67
    uga
    -0.65
    76561
    -0.63
    esses
    -0.63
    Sund
    -0.62
    POSITIVE LOGITS
    imensional
    1.30
     printer
    1.17
     printers
    1.15
     printing
    1.14
     Printing
    1.11
     Printed
    1.06
     printed
    1.05
    printed
    0.99
     Realms
    0.91
    Mark
    0.90
    Activations Density 0.065%

    No Known Activations