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. 8-RES-JB
    6. 9526
    Prev
    Next
    INDEX
    Explanations

    phrases that involve two distinct entities or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to pairs of entities or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utory
    -0.66
     quarry
    -0.64
    nce
    -0.63
    pter
    -0.63
    =-=-
    -0.62
     Newsletter
    -0.62
    ogle
    -0.61
    pta
    -0.61
    lé
    -0.60
    arah
    -0.59
    POSITIVE LOGITS
     sexes
    1.04
     simultaneously
    1.04
    paces
    0.99
     equally
    0.95
     halves
    0.88
     respectively
    0.87
     alike
    0.86
     concurrently
    0.86
     sides
    0.85
    hips
    0.84
    Activations Density 0.189%

    No Known Activations