© 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. 7-RES-JB
    11. 21637
    Prev
    Next
    INDEX
    Explanations

    text related to something being capable of performing an action or having a certain quality

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express capability or potential

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coffin
    -0.69
     Bans
    -0.67
    era
    -0.63
    cloth
    -0.62
    isite
    -0.60
    govtrack
    -0.60
    book
    -0.60
     Gazette
    -0.59
     Directions
    -0.59
     Dollar
    -0.58
    POSITIVE LOGITS
     withstand
    0.97
     inflicting
    0.89
     distinguishing
    0.79
     storing
    0.77
     detecting
    0.77
     handling
    0.77
     foresee
    0.76
     delivering
    0.76
     interpreting
    0.74
     reaching
    0.74
    Activations Density 0.095%

    No Known Activations