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. 1-RES-JB
    6. 6102
    Prev
    Next
    INDEX
    Explanations

    references to the card game "Spades" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "trades" or related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kaufman
    -0.62
    shoot
    -0.61
     socket
    -0.61
    %]
    -0.58
    oenix
    -0.58
     personal
    -0.55
     mutual
    -0.55
    Phys
    -0.55
     hybrid
    -0.54
     holster
    -0.54
    POSITIVE LOGITS
    ades
    1.28
    chool
    0.98
    ading
    0.82
    hi
    0.81
    aders
    0.79
    cles
    0.78
    ildo
    0.78
    ffiti
    0.77
    cliffe
    0.76
    ader
    0.75
    Activations Density 0.007%

    No Known Activations