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. 7-RES-JB
    6. 4681
    Prev
    Next
    INDEX
    Explanations

    numerical values representing kilometers

    oai_token-act-pair · gpt-3.5-turbo

    quantitative measurements of distance expressed in kilometers or miles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tek
    -0.70
    gotten
    -0.69
     Crunch
    -0.64
    FORE
    -0.62
     Wong
    -0.60
    Irish
    -0.59
     Gems
    -0.57
    ividual
    -0.57
    humans
    -0.57
    fly
    -0.57
    POSITIVE LOGITS
     km
    0.92
    ²
    0.90
    km
    0.90
     kilometers
    0.89
     kilometres
    0.85
    assing
    0.83
    ometers
    0.81
     radius
    0.76
    iking
    0.75
    assed
    0.74
    Activations Density 0.022%

    No Known Activations