© 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. 0-RES-JB
    11. 9680
    Prev
    Next
    INDEX
    Explanations

    procedures or objects related to tubes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of tubes or tubing

    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
     Assets
    -0.77
     Mich
    -0.77
     Fors
    -0.75
     Seraph
    -0.74
     McKin
    -0.73
     Luck
    -0.73
     Ning
    -0.72
    rien
    -0.71
     Shawn
    -0.71
     Laksh
    -0.70
    POSITIVE LOGITS
     tube
    3.89
     tubes
    3.45
     Tube
    3.08
    tube
    3.04
    Tube
    2.34
     tubing
    1.92
     tub
    1.53
    ubes
    1.43
    tub
    1.33
     cylinder
    1.21
    Activations Density 0.022%

    No Known Activations