© 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. 8-RES-JB
    11. 17784
    Prev
    Next
    INDEX
    Explanations

    results or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases or sentences that indicate results or outcomes

    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
    NetMessage
    -0.73
    osponsors
    -0.68
    udi
    -0.68
     blat
    -0.67
    tera
    -0.66
     Spur
    -0.64
     Passage
    -0.63
    thur
    -0.62
    cale
    -0.62
    cellaneous
    -0.62
    POSITIVE LOGITS
    iveness
    0.89
     thereof
    0.85
    ivity
    0.81
    ively
    0.75
     of
    0.70
     result
    0.70
    arian
    0.69
    ivism
    0.68
    ivist
    0.67
    aries
    0.65
    Activations Density 0.048%

    No Known Activations