Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15098
    Prev
    Next
    INDEX
    Explanations

    phrases related to American football defense

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to defensive positions and strategies in football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Investig
    -0.64
     Hirosh
    -0.64
    uble
    -0.63
    pired
    -0.63
     Wander
    -0.63
     Nirvana
    -0.62
     Nest
    -0.60
     Editorial
    -0.60
     Franç
    -0.60
     1899
    -0.60
    POSITIVE LOGITS
     linebackers
    1.18
     linebacker
    1.14
     receivers
    1.11
     linemen
    1.08
     routes
    1.04
     lineback
    1.03
     backfield
    1.01
     cornerback
    1.01
     formations
    0.97
     zone
    0.96
    Activations Density 0.159%

    No Known Activations