© 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. 10-RES-JB
    11. 5343
    Prev
    Next
    INDEX
    Explanations

    references to the Stanley Cup, a prestigious ice hockey trophy

    oai_token-act-pair · gpt-3.5-turbo

    references to the Stanley Cup

    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
    á½
    -0.84
    ged
    -0.81
    Reviewer
    -0.81
    ships
    -0.73
    eer
    -0.73
    gew
    -0.71
    metic
    -0.71
    dress
    -0.70
    ynt
    -0.70
    esis
    -0.69
    POSITIVE LOGITS
     Kubrick
    1.11
     Cup
    1.08
     Cups
    1.00
     Trophy
    0.85
     Stanley
    0.79
     Lumpur
    0.78
     Baldwin
    0.78
    lihood
    0.73
     Clinic
    0.71
     Churchill
    0.71
    Activations Density 0.035%

    No Known Activations