© 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. 3-RES-JB
    11. 17106
    Prev
    Next
    INDEX
    Explanations

    the word 'to'

    oai_token-act-pair · gpt-3.5-turbo

    the pattern of the phrase "seems to" and its variations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    listed
    -0.91
    quickShipAvailable
    -0.67
     awaits
    -0.62
     drafts
    -0.62
    posted
    -0.62
     Appears
    -0.62
     listings
    -0.61
     Advertisement
    -0.60
    _.
    -0.59
    Reviewed
    -0.58
    POSITIVE LOGITS
     be
    1.14
     give
    1.10
     eat
    1.08
     make
    1.03
     perform
    1.03
     incorporate
    1.01
     settle
    0.99
     behave
    0.98
     improve
    0.98
    othy
    0.97
    Activations Density 0.371%

    No Known Activations