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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 4700
    Prev
    Next
    INDEX
    Explanations

    measurements related to length or distance, particularly the term "inch"

    oai_token-act-pair · gpt-3.5-turbo

    measurements of physical dimensions or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifiers
    -0.73
    bos
    -0.65
    uits
    -0.65
    uates
    -0.64
     Rab
    -0.62
     roles
    -0.62
     Compensation
    -0.62
    ifications
    -0.61
    Mis
    -0.61
     crowds
    -0.61
    POSITIVE LOGITS
     inch
    3.12
     ounce
    2.62
     acre
    1.32
     pound
    1.31
    inch
    1.31
     gallon
    1.22
     hour
    1.21
     metre
    1.18
    imeter
    1.08
     mile
    1.08
    Activations Density 0.016%

    No Known Activations