© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 5764
    Prev
    Next
    INDEX
    Explanations

    words related to advertisements and promotion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to advertisement and marketing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.64
    _>
    -0.63
    00007
    -0.62
     coughing
    -0.61
     inconven
    -0.59
    omore
    -0.59
    ¬¼
    -0.59
     refere
    -0.58
    taboola
    -0.58
    NetMessage
    -0.58
    POSITIVE LOGITS
    istration
    0.87
    aline
    0.86
    phe
    0.85
    itness
    0.78
    aida
    0.74
    ainment
    0.73
    vertisement
    0.72
    asio
    0.72
    raid
    0.70
    andise
    0.70
    Activations Density 0.048%

    No Known Activations