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. 9-RES-JB
    6. 15051
    Prev
    Next
    INDEX
    Explanations

    speed measurements expressed in miles or kilometers per hour

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to rates, specifically measurements involving "per" and other quantifiable expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gat
    -0.66
    Tal
    -0.65
    naires
    -0.64
    FORE
    -0.63
     giveaways
    -0.62
    Newsletter
    -0.61
    ulas
    -0.60
    downs
    -0.59
     Sloan
    -0.59
    Desktop
    -0.59
    POSITIVE LOGITS
     gallon
    0.86
     hour
    0.85
    imeters
    0.73
     cubic
    0.73
    hour
    0.71
     capita
    0.70
     ann
    0.69
     voyage
    0.66
     hr
    0.66
    imeter
    0.66
    Activations Density 0.036%

    No Known Activations