© 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. 11-RES-JB
    11. 12690
    Prev
    Next
    INDEX
    Explanations

    phrases describing something moving or transitioning to a different location or state

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.71
    entimes
    -0.66
    kan
    -0.66
    cu
    -0.65
    killer
    -0.64
    eka
    -0.62
    say
    -0.62
    Tips
    -0.61
    ----------------------------------------------------------------
    -0.60
    igh
    -0.60
    POSITIVE LOGITS
     adulthood
    1.12
     orbit
    0.88
     existence
    0.88
     unch
    0.87
     ob
    0.85
     obscurity
    0.78
    jected
    0.78
     classrooms
    0.77
     submission
    0.76
     infinity
    0.76
    Activations Density 0.116%

    No Known Activations