© 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. 20344
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical objects, especially cables

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cables and related wiring components

    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
     Herb
    -0.73
     Rooney
    -0.72
    stad
    -0.70
    Tax
    -0.68
     Schwarz
    -0.68
    eworld
    -0.67
     Soy
    -0.67
    estate
    -0.66
     Sunni
    -0.64
    zai
    -0.64
    POSITIVE LOGITS
     cables
    1.81
     cable
    1.24
     cords
    1.04
     wires
    0.99
     sleeves
    0.97
     ropes
    0.96
     piping
    0.87
    mith
    0.86
     seams
    0.86
     tubes
    0.86
    Activations Density 0.013%

    No Known Activations