© 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. 3-RES-JB
    11. 11279
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to practice or training activities

    oai_token-act-pair · gpt-3.5-turbo

    references to drills or training exercises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.77
     Leilan
    -0.73
    Reloaded
    -0.70
    é¾įå
    -0.69
    CHO
    -0.69
     Hep
    -0.69
     Governments
    -0.68
     Represent
    -0.67
    HCR
    -0.67
    debian
    -0.66
    POSITIVE LOGITS
     drilled
    1.29
     drill
    1.22
     drilling
    1.04
     Drill
    1.02
     drills
    1.01
     sergeant
    0.99
    itud
    0.98
     instructor
    0.83
     rigs
    0.81
     digs
    0.79
    Activations Density 0.008%

    No Known Activations