© 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. 0-RES-JB
    11. 5387
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Crunch"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific company or brand, "Crunch."

    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
    smanship
    -0.74
    Join
    -0.74
    pter
    -0.67
    case
    -0.66
    slot
    -0.64
    cube
    -0.64
    orously
    -0.64
     largeDownload
    -0.63
    paralle
    -0.62
     Finder
    -0.61
    POSITIVE LOGITS
     being
    1.27
    being
    0.88
     Being
    0.82
    BILITIES
    0.65
    ICK
    0.63
     becoming
    0.62
    inx
    0.61
     Rouge
    0.61
    inian
    0.61
     Commun
    0.60
    Activations Density 0.000%

    No Known Activations