© 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. 17247
    Prev
    Next
    INDEX
    Explanations

    phrases signifying emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    the word "obviously" and its variations

    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
    aeus
    -0.79
    aily
    -0.76
    arthed
    -0.75
    animous
    -0.74
    burg
    -0.73
    aeper
    -0.71
    ths
    -0.70
    berman
    -0.70
    enta
    -0.69
    aments
    -0.68
    POSITIVE LOGITS
     outnumbered
    0.77
     benefited
    0.66
     infringing
    0.64
     preceded
    0.63
     caused
    0.63
     influenced
    0.63
     effected
    0.61
     affected
    0.61
     upset
    0.61
    س
    0.61
    Activations Density 0.061%

    No Known Activations