© 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. 6-RES-JB
    11. 7977
    Prev
    Next
    INDEX
    Explanations

    instances of the word "random" or variations of the word like "randomized" and "randomness"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "random" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gur
    -0.84
    ModLoader
    -0.82
    ports
    -0.77
    dain
    -0.76
    ippi
    -0.72
    raints
    -0.71
    nai
    -0.71
    helle
    -0.70
    toc
    -0.70
    iao
    -0.70
    POSITIVE LOGITS
     assortment
    1.05
    izer
    0.94
    istically
    0.93
    ised
    0.90
     randomly
    0.83
    ization
    0.82
    izable
    0.81
    isable
    0.79
    aneously
    0.79
    izers
    0.77
    Activations Density 0.029%

    No Known Activations