Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 19144
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "All."

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing collective or inclusive sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utch
    -0.64
    ciation
    -0.64
    NT
    -0.57
    rir
    -0.57
    OUNT
    -0.56
    utor
    -0.55
    Returns
    -0.55
    bal
    -0.54
    EStream
    -0.53
    argon
    -0.53
    POSITIVE LOGITS
    owing
    1.33
    iances
    1.27
    iance
    1.10
    ergic
    1.04
     indications
    1.04
     bets
    1.03
    uding
    1.02
     kidding
    1.01
    owed
    1.00
    ocate
    0.92
    Activations Density 0.061%

    No Known Activations