© 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. 3-RES-JB
    11. 3995
    Prev
    Next
    INDEX
    Explanations

    references to the soccer team "Real Madrid"

    oai_token-act-pair · gpt-3.5-turbo

    references to the football club Real Madrid

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rieved
    -0.84
    onies
    -0.80
     Vance
    -0.69
    rogen
    -0.69
    andering
    -0.69
    ollow
    -0.68
    owder
    -0.67
    roleum
    -0.67
    ttes
    -0.66
    served
    -0.65
    POSITIVE LOGITS
     Madrid
    1.01
     Inquisition
    0.85
     Ronaldo
    0.78
    mers
    0.77
    ÃŃa
    0.71
    illo
    0.71
     Munich
    0.70
     Liga
    0.70
    Leaks
    0.69
     Barcelona
    0.67
    Activations Density 0.010%

    No Known Activations