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

    Neuronpedia

    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. 2-RES-JB
    11. 17615
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Barton."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    determination
    -0.80
    ebook
    -0.73
    egg
    -0.69
    itability
    -0.67
    odiac
    -0.67
    hh
    -0.66
    rolog
    -0.63
    clinical
    -0.62
     digits
    -0.61
    demand
    -0.60
    POSITIVE LOGITS
     Barton
    1.31
     Springs
    0.99
    bent
    0.90
    wick
    0.88
    boro
    0.84
    leigh
    0.79
    ouf
    0.79
    minster
    0.77
    ville
    0.77
    mont
    0.76
    Activations Density 0.009%

    No Known Activations