© 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. 4-RES-JB
    11. 22642
    Prev
    Next
    INDEX
    Explanations

    instances of the word "clone" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "clone" and its variations

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

    No Comments

    Negative Logits
    ourning
    -0.84
    erred
    -0.83
    Population
    -0.79
    akh
    -0.76
    tri
    -0.76
    alties
    -0.75
    Topics
    -0.74
    orney
    -0.72
    akening
    -0.69
    lower
    -0.69
    POSITIVE LOGITS
     clones
    1.06
     trooper
    1.04
     clone
    1.00
     troopers
    0.90
     Clone
    0.75
     Yamato
    0.74
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.73
     Doodle
    0.72
    oning
    0.71
     Trooper
    0.70
    Activations Density 0.016%

    No Known Activations