© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 7161
    Prev
    Next
    INDEX
    Explanations

    references to car brands and some related terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cro
    -0.88
     Osw
    -0.86
    nian
    -0.85
     yarn
    -0.80
    wu
    -0.80
    aina
    -0.80
     Meow
    -0.79
     Cro
    -0.79
    oire
    -0.77
     Witches
    -0.73
    POSITIVE LOGITS
     automotive
    2.07
     automakers
    2.03
     driver
    1.96
     drivers
    1.95
     Drivers
    1.93
     automobile
    1.87
     Driver
    1.87
     cars
    1.87
     Volvo
    1.85
    Driver
    1.83
    Activations Density 0.855%

    No Known Activations