© 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. 1639
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, specifically the name "Nawaz."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names, particularly those relating to individuals and locations

    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
    furt
    -0.79
     Minotaur
    -0.78
    ipel
    -0.72
    ocaust
    -0.70
    ople
    -0.69
    ampire
    -0.69
     Rite
    -0.68
     Spartans
    -0.66
     Vampire
    -0.65
    ously
    -0.64
    POSITIVE LOGITS
     Naw
    0.99
    rooms
    0.83
    hew
    0.76
    \/\/
    0.75
    ean
    0.71
    eor
    0.68
    AMI
    0.68
    Ø
    0.68
    aiman
    0.67
    igh
    0.67
    Activations Density 0.016%

    No Known Activations