© 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. 7-RES-JB
    11. 14362
    Prev
    Next
    INDEX
    Explanations

    instances of the word "have" followed by the number 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "have."

    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
     capable
    -0.66
     typing
    -0.65
     incapable
    -0.65
     distributing
    -0.65
    immune
    -0.64
     plotting
    -0.63
     transporting
    -0.62
     performing
    -0.62
     preparing
    -0.62
     responsible
    -0.61
    POSITIVE LOGITS
     been
    1.23
     Been
    1.04
     arisen
    1.03
    been
    0.98
     emerged
    0.97
     existed
    0.86
     undergone
    0.85
     become
    0.84
     risen
    0.84
    thren
    0.82
    Activations Density 0.055%

    No Known Activations