© 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 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. 0-RES-JB
    11. 20467
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Car'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the character or element "Car."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itiz
    -0.76
    wu
    -0.69
    uminati
    -0.68
    Allah
    -0.67
    swing
    -0.65
    Å«
    -0.65
    utsu
    -0.65
    rel
    -0.65
    miss
    -0.64
    unity
    -0.62
    POSITIVE LOGITS
     Car
    3.50
    Car
    2.41
    car
    1.96
     Cars
    1.92
     CAR
    1.89
     car
    1.65
    CAR
    1.62
     Carrier
    1.36
     Cat
    1.32
     Cab
    1.29
    Activations Density 0.021%

    No Known Activations