© 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. 14499
    Prev
    Next
    INDEX
    Explanations

    references to a specific term - "Bronco"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Bronco."

    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
    Assembly
    -0.68
    scape
    -0.68
    espie
    -0.68
    ordinary
    -0.67
     Vide
    -0.67
    visual
    -0.65
     Angels
    -0.64
     Monarch
    -0.63
    bsp
    -0.63
     Sorceress
    -0.62
    POSITIVE LOGITS
    ners
    0.88
    fman
    0.84
    ettes
    0.78
    anche
    0.78
    kh
    0.77
    kus
    0.77
    itionally
    0.76
    ald
    0.75
    ny
    0.75
    nuts
    0.73
    Activations Density 0.054%

    No Known Activations