© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12923
    Prev
    Next
    INDEX
    Explanations

    the word "the" occurring before a certain point in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    abi
    -0.80
    amsung
    -0.74
    pport
    -0.71
     propagate
    -0.69
    ibaba
    -0.68
     preceded
    -0.65
    agascar
    -0.64
    ochond
    -0.63
    ARI
    -0.62
    etsk
    -0.62
    POSITIVE LOGITS
     end
    0.98
     sheer
    0.90
     same
    0.84
     Numbers
    0.83
     margins
    0.82
     outset
    0.77
     widest
    0.77
     way
    0.75
     usual
    0.75
     fireplace
    0.74
    Activations Density 0.096%

    No Known Activations