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. 23413
    Prev
    Next
    INDEX
    Explanations

    phrases related to various sports events and competitions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in" and its contextual uses

    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
    20439
    -0.67
    igion
    -0.65
     Investig
    -0.63
      
    -0.63
    NOW
    -0.62
    Detect
    -0.62
    Insp
    -0.61
    oldown
    -0.60
     Helpful
    -0.59
    Companies
    -0.59
    POSITIVE LOGITS
     contention
    1.25
    ching
    0.98
     jeopardy
    0.97
     trouble
    0.95
     limbo
    0.85
     danger
    0.83
     prime
    0.83
     decline
    0.82
    inventoryQuantity
    0.81
     flux
    0.79
    Activations Density 0.125%

    No Known Activations