© 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. 9-RES-JB
    11. 13962
    Prev
    Next
    INDEX
    Explanations

    technology-related terms, specifically versions or releases of software or games

    oai_token-act-pair · gpt-3.5-turbo

    specific software and game versions or adaptations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loads
    -0.80
    arers
    -0.73
    icians
    -0.72
    brid
    -0.71
    akers
    -0.70
    aways
    -0.69
    urches
    -0.68
     makers
    -0.65
    immers
    -0.65
    pleting
    -0.65
    POSITIVE LOGITS
     playbook
    0.72
    /,
    0.71
     Codec
    0.66
     Digest
    0.64
     Puzzle
    0.64
     Intermediate
    0.62
     puzzle
    0.62
     Magnus
    0.62
     Tycoon
    0.61
     greeting
    0.61
    Activations Density 0.421%

    No Known Activations