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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 10321
    Prev
    Next
    INDEX
    Explanations

    terms related to drilling, either literally (i.e., drilling for oil) or metaphorically (i.e., drilling down into data)

    oai_token-act-pair · gpt-3.5-turbo

    references to drills or drilling activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CHO
    -0.76
     Actress
    -0.71
     Leilan
    -0.68
     Hep
    -0.65
     Reincarn
    -0.64
    eto
    -0.64
    é¾įå
    -0.63
     Hope
    -0.62
     Library
    -0.62
    BuyableInstoreAndOnline
    -0.62
    POSITIVE LOGITS
     drilled
    1.22
     drill
    1.17
     sergeant
    1.07
     drilling
    1.04
     drills
    1.03
    itud
    0.91
     Drill
    0.91
     rigs
    0.86
     holes
    0.81
    atre
    0.76
    Activations Density 0.042%

    No Known Activations