© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 10794
    Prev
    Next
    INDEX
    Explanations

    specific mentions of car models and details like years, makes, and colors

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific car makes and models

    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
     Flavoring
    -0.85
    ertodd
    -0.80
    cffff
    -0.79
    sites
    -0.77
     pamph
    -0.75
    glers
    -0.74
    tumblr
    -0.73
    papers
    -0.73
    ucl
    -0.71
    utenberg
    -0.69
    POSITIVE LOGITS
     sedan
    1.44
     SUV
    1.24
     convertible
    1.15
     Cadillac
    1.15
     Mercedes
    1.09
     racer
    1.03
     Corvette
    1.03
     chassis
    1.03
     Jaguar
    1.01
     BMW
    1.00
    Activations Density 0.149%

    No Known Activations