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. 4-RES-JB
    6. 8308
    Prev
    Next
    INDEX
    Explanations

    distances expressed in kilometers

    oai_token-act-pair · gpt-3.5-turbo

    instances of distance measurements in kilometers

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

    No Comments

    Negative Logits
     Gott
    -0.68
    tek
    -0.65
     bearer
    -0.63
     Semin
    -0.62
    ERY
    -0.61
     Crunch
    -0.61
    FORE
    -0.60
     Suc
    -0.59
    BACK
    -0.59
    gotten
    -0.58
    POSITIVE LOGITS
     km
    1.02
    km
    1.01
     kilometres
    0.86
     kilometers
    0.85
    assing
    0.81
    iking
    0.78
    airo
    0.78
    +)
    0.77
    imet
    0.75
    ijk
    0.74
    Activations Density 0.018%

    No Known Activations