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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18974
    Prev
    Next
    INDEX
    Explanations

    phrases related to helping strangers with cars, particularly in difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the plural form of nouns

    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
    wu
    -0.93
    warts
    -0.90
    Å«
    -0.86
     Meow
    -0.83
    Cro
    -0.83
     microbiome
    -0.81
    Psy
    -0.80
    nian
    -0.80
    wich
    -0.79
     Guant
    -0.78
    POSITIVE LOGITS
     Cars
    2.00
     cars
    2.00
     car
    1.98
     automotive
    1.87
     Vehicle
    1.85
     vehicle
    1.85
     automobile
    1.85
     vehicles
    1.77
     automobiles
    1.75
     Drivers
    1.73
    Activations Density 0.507%

    No Known Activations