© 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. 1-RES-JB
    11. 9567
    Prev
    Next
    INDEX
    Explanations

    mentions of creating duplicates or copies

    oai_token-act-pair · gpt-3.5-turbo

    references to cloning and clones

    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
    Topics
    -0.81
    ourning
    -0.79
    erred
    -0.78
    alties
    -0.75
    edin
    -0.75
    isconsin
    -0.73
    akening
    -0.73
    ashington
    -0.71
    arching
    -0.70
    icrobial
    -0.70
    POSITIVE LOGITS
     clones
    1.36
     clone
    1.16
     trooper
    1.02
     Clone
    0.90
     troopers
    0.89
     Yamato
    0.82
     Doodle
    0.77
     Trooper
    0.76
     Eclipse
    0.72
     dolls
    0.72
    Activations Density 0.008%

    No Known Activations