© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6860
    Prev
    Next
    INDEX
    Explanations

    words related to knitting or tight fastening objects

    oai_token-act-pair · gpt-3.5-turbo

    references to "kn" as a prefix in various words

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    DEM
    -0.83
    IUM
    -0.81
     Gum
    -0.78
    geist
    -0.73
    grounds
    -0.72
     Popular
    -0.72
    Relations
    -0.70
    due
    -0.69
     Ducks
    -0.68
    hazard
    -0.68
    POSITIVE LOGITS
     kn
    1.21
    uckle
    1.12
    itted
    1.04
    uckles
    0.96
     quir
    0.96
    ocking
    0.94
    kn
    0.91
    ivable
    0.90
    ĵĺ
    0.90
    ickers
    0.88
    Activations Density 0.006%

    No Known Activations