© 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. 10-RES-JB
    11. 11234
    Prev
    Next
    INDEX
    Explanations

    statements attributed to individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of proper nouns, particularly titles and names

    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
     livest
    -0.82
    wcs
    -0.79
     unden
    -0.78
    anwhile
    -0.78
    arily
    -0.77
    ioned
    -0.72
    cember
    -0.69
     destro
    -0.69
     charact
    -0.67
     encount
    -0.67
    POSITIVE LOGITS
     Robot
    0.99
     Bezos
    0.95
     Speaker
    0.94
     Spock
    0.94
     Weasley
    0.94
     Snowden
    0.93
     Obama
    0.93
     Trump
    0.92
     McMahon
    0.92
     Musk
    0.92
    Activations Density 0.038%

    No Known Activations