© 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 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. 8-RES-JB
    11. 1044
    Prev
    Next
    INDEX
    Explanations

    names of individuals or players in a team-related context

    oai_token-act-pair · gpt-3.5-turbo

    parentheses and their nested structures in the text, particularly those associated with team names or groupings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meaning
    -0.69
     meanings
    -0.67
    meaning
    -0.64
     conventions
    -0.64
     customary
    -0.64
     meaning
    -0.63
    devices
    -0.62
    eatures
    -0.62
     definitions
    -0.62
     assum
    -0.62
    POSITIVE LOGITS
     Jr
    1.29
    Jr
    0.99
    Assistant
    0.85
     PhD
    0.85
     Sr
    0.79
     QC
    0.75
     MD
    0.72
     TBA
    0.72
     pers
    0.68
    ;;;;;;;;;;;;
    0.67
    Activations Density 0.209%

    No Known Activations