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. 1-RES-JB
    6. 16639
    Prev
    Next
    INDEX
    Explanations

    measurements expressed in millimeters or centimeters

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "centimeter" and related measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isSpecialOrderable
    -0.69
     Angry
    -0.65
     unfortunate
    -0.65
    versions
    -0.64
    bound
    -0.63
     sorely
    -0.63
    burning
    -0.60
    selection
    -0.59
    CVE
    -0.59
     conditioning
    -0.59
    POSITIVE LOGITS
    imet
    1.77
    imeters
    0.97
    imeter
    0.86
    terness
    0.83
    yip
    0.82
    imore
    0.80
    pees
    0.80
    ascus
    0.79
    awei
    0.78
     glim
    0.77
    Activations Density 0.007%

    No Known Activations