© 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. 9-RES-JB
    11. 10381
    Prev
    Next
    INDEX
    Explanations

    names of individuals with titles or positions, such as "Dr." or "Judge."

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people, particularly those with professional titles or roles, such as "Dr." or "Professor."

    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
     date
    -0.69
     reins
    -0.63
     vortex
    -0.63
     mainland
    -0.62
     grid
    -0.62
     processing
    -0.61
     skate
    -0.60
     Eleven
    -0.59
     thieves
    -0.59
     surfing
    -0.59
    POSITIVE LOGITS
    âĸĪâĸĪâĸĪâĸĪ
    1.15
    keley
    0.95
    agall
    0.95
    ordan
    0.94
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.89
    ij士
    0.84
    raq
    0.82
    obia
    0.80
    anus
    0.79
    lesh
    0.79
    Activations Density 0.267%

    No Known Activations