© 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 EvalsExportsinterp-engineNEWAPI 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. 5559
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals or groups involved in events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to individuals involved in specific events or incidents

    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
     highs
    -0.67
    olerance
    -0.66
    enture
    -0.66
    umption
    -0.63
    Growing
    -0.63
    ð
    -0.63
     practice
    -0.61
     shorthand
    -0.60
    ital
    -0.60
     release
    -0.59
    POSITIVE LOGITS
     Cosponsors
    0.90
     unidentified
    0.81
     unnamed
    0.81
     elderly
    0.77
     Huma
    0.75
     Markus
    0.75
     Aless
    0.73
     Ake
    0.72
     Mahmoud
    0.72
     Kumar
    0.71
    Activations Density 0.863%

    No Known Activations