© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 20259
    Prev
    Next
    INDEX
    Explanations

    mention of health-related topics, particularly regarding blood pressure and circulation in the brain

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a relationship or association with something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    escription
    -0.84
    itably
    -0.81
    ividual
    -0.73
     withd
    -0.72
    agate
    -0.68
    rahim
    -0.67
    ecause
    -0.66
    enegger
    -0.65
    uilt
    -0.65
    ammers
    -0.64
    POSITIVE LOGITS
     of
    1.64
     thereof
    1.22
     OF
    1.17
    of
    1.04
    Of
    1.03
     Of
    1.02
    OF
    0.87
    76561
    0.71
    oft
    0.65
    natureconservancy
    0.62
    Activations Density 0.948%

    No Known Activations