© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 6895
    Prev
    Next
    INDEX
    Explanations

    descriptions related to debates or controversies around public monuments or statues

    oai_token-act-pair · gpt-3.5-turbo

    references to political discourse and symbolism

    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
    inar
    -0.81
    inki
    -0.80
    irlf
    -0.79
     Startup
    -0.77
     Flavoring
    -0.73
    ducers
    -0.73
     Outbreak
    -0.72
     agile
    -0.72
    Crunch
    -0.70
     Advantage
    -0.70
    POSITIVE LOGITS
     monument
    1.90
     statues
    1.89
     monuments
    1.86
     statue
    1.79
     memorial
    1.76
     plaque
    1.55
     Monument
    1.48
     sculptures
    1.45
     commemor
    1.44
     Statue
    1.43
    Activations Density 0.386%

    No Known Activations