© 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. 11-RES-JB
    11. 255
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals named "Car" or similar variations

    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
    naires
    -0.72
    é¾įå¥ij士
    -0.69
     FW
    -0.65
    EngineDebug
    -0.63
    043
    -0.63
     MSG
    -0.63
     DSL
    -0.62
     EW
    -0.60
    ELD
    -0.59
     aloud
    -0.57
    POSITIVE LOGITS
    riage
    1.40
    negie
    1.35
    rots
    1.34
    riers
    1.32
    ousel
    1.29
    acas
    1.28
    leton
    1.23
    olina
    1.22
    avan
    1.22
    amel
    1.19
    Activations Density 0.036%

    No Known Activations