© 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. 1-RES-JB
    11. 20418
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Tim"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tim."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    76561
    -0.88
    Magikarp
    -0.70
    ãģĨ
    -0.68
    ãĤĵ
    -0.67
    Untitled
    -0.66
    hazard
    -0.66
    EngineDebug
    -0.65
    avorite
    -0.64
     apprehend
    -0.63
    KI
    -0.63
    POSITIVE LOGITS
    estamp
    1.26
     Ferr
    1.02
    othy
    0.97
    oleon
    0.95
    bre
    0.94
    oshenko
    0.94
     Tim
    0.94
    mons
    0.88
    othe
    0.84
    Tim
    0.83
    Activations Density 0.006%

    No Known Activations