© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 22613
    Prev
    Next
    INDEX
    Explanations

    phrases related to public sentiment and opinion

    oai_token-act-pair · gpt-3.5-turbo

    discourse surrounding public opinion and sentiment on social issues

    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
    »Ĵ
    -0.89
     Processor
    -0.72
    atron
    -0.70
    breaker
    -0.69
     Swordsman
    -0.63
    iologist
    -0.62
    ishable
    -0.61
     terminating
    -0.60
    ©¶æ¥µ
    -0.60
     expires
    -0.59
    POSITIVE LOGITS
     discontent
    1.56
     enthusiasm
    1.54
     skepticism
    1.52
     concern
    1.52
     hysteria
    1.49
     une
    1.49
     outcry
    1.49
     dissatisfaction
    1.47
     indignation
    1.46
     awareness
    1.46
    Activations Density 0.376%

    No Known Activations