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. 24234
    Prev
    Next
    INDEX
    Explanations

    mentions of the animal "cougar"

    oai_token-act-pair · gpt-3.5-turbo

    references to cougars

    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
    aceutical
    -0.80
     Pilgrim
    -0.72
     Faster
    -0.68
    Downloadha
    -0.67
     guiActiveUnfocused
    -0.67
    iary
    -0.66
     Frie
    -0.66
     Shed
    -0.65
     Fabric
    -0.65
     Nanto
    -0.65
    POSITIVE LOGITS
    riers
    1.24
    rier
    1.05
    pe
    1.04
    plet
    1.04
    pper
    0.98
    ps
    0.96
    chet
    0.94
    pa
    0.91
    gars
    0.88
    ple
    0.88
    Activations Density 0.019%

    No Known Activations