© 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. 9-RES-JB
    11. 10072
    Prev
    Next
    INDEX
    Explanations

    names of sports teams or athletes, particularly focusing on a specific team named "Tiger"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Tiger" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibel
    -0.84
    inventoryQuantity
    -0.73
    Constructed
    -0.69
    ĵĺ
    -0.69
    atform
    -0.69
    ++++++++++++++++
    -0.67
    idge
    -0.67
    EngineDebug
    -0.66
    iversal
    -0.65
    phabet
    -0.63
    POSITIVE LOGITS
     Woods
    1.03
     Tigers
    1.01
     Tiger
    0.82
    bol
    0.81
    emonium
    0.81
    opard
    0.78
    gers
    0.77
    ures
    0.74
    culosis
    0.73
     Swan
    0.71
    Activations Density 0.072%

    No Known Activations