© 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. 6-RES-JB
    11. 2847
    Prev
    Next
    INDEX
    Explanations

    instances of the word "broken."

    oai_token-act-pair · gpt-3.5-turbo

    the word "broken" in various contexts

    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
    minist
    -0.87
    anamo
    -0.84
    utra
    -0.83
    urai
    -0.83
    ittee
    -0.76
    itatively
    -0.73
    azor
    -0.73
    udic
    -0.73
    yss
    -0.72
    aeda
    -0.72
    POSITIVE LOGITS
    hearted
    0.93
    neck
    0.91
     bones
    0.83
    bones
    0.81
     ribs
    0.76
     necks
    0.74
    adoes
    0.73
    broken
    0.73
     hearts
    0.72
    heart
    0.71
    Activations Density 0.031%

    No Known Activations