© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15159
    Prev
    Next
    INDEX
    Explanations

    mentions of sharp objects generally associated with cutting or shaving

    oai_token-act-pair · gpt-3.5-turbo

    terms related to razors and shaving

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eeds
    -0.70
     Park
    -0.69
     Belg
    -0.67
     Ka
    -0.67
     âĺħ
    -0.65
     Flood
    -0.65
     Seoul
    -0.64
     Parks
    -0.64
     Missions
    -0.63
     Station
    -0.63
    POSITIVE LOGITS
     razor
    3.76
     Razor
    3.04
     shave
    2.08
     shaving
    2.07
    azor
    1.79
     Raz
    1.54
     shaved
    1.45
     scissors
    1.14
     shampoo
    1.06
     blades
    1.03
    Activations Density 0.043%

    No Known Activations