© 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. 6-RES-JB
    11. 2850
    Prev
    Next
    INDEX
    Explanations

    names of individuals or organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of people, places, and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    example
    -0.69
    ************
    -0.64
    Ń·
    -0.63
    shapeshifter
    -0.63
    >>\
    -0.62
    aterasu
    -0.60
    romeda
    -0.60
    âĢķ
    -0.59
    $.
    -0.59
    olkien
    -0.59
    POSITIVE LOGITS
     Emails
    0.73
     reacts
    0.69
    ulic
    0.63
    rieving
    0.62
    holder
    0.62
    mite
    0.60
     bets
    0.60
    mania
    0.60
     presses
    0.57
    fighters
    0.57
    Activations Density 0.219%

    No Known Activations