© 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. 10-RES-JB
    11. 13855
    Prev
    Next
    INDEX
    Explanations

    references to the automobile company "Ford."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Ford"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quo
    -0.69
     Flavoring
    -0.65
     Sakuya
    -0.64
     certific
    -0.63
     cannabin
    -0.63
     paras
    -0.63
    udic
    -0.62
     huh
    -0.62
    stract
    -0.62
     surfing
    -0.61
    POSITIVE LOGITS
    ham
    1.20
     Motor
    1.02
     Mustang
    0.92
     Fiesta
    0.88
    ragon
    0.83
    shire
    0.83
     Focus
    0.82
    clad
    0.82
    Ford
    0.80
    isle
    0.77
    Activations Density 0.018%

    No Known Activations