© 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. 6-RES-JB
    11. 14947
    Prev
    Next
    INDEX
    Explanations

    phrases related to skepticism and criticism

    oai_token-act-pair · gpt-3.5-turbo

    sentiments expressing skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bryce
    -0.69
     Originally
    -0.62
     Modified
    -0.61
     leased
    -0.61
     Arri
    -0.60
     Bangalore
    -0.60
    netflix
    -0.59
     Canaveral
    -0.58
     Located
    -0.58
     Built
    -0.56
    POSITIVE LOGITS
     conclusions
    0.85
     reader
    0.75
    odox
    0.74
     journalistic
    0.72
    ensical
    0.71
     readers
    0.70
     eluc
    0.70
     oneself
    0.70
     decipher
    0.70
    entious
    0.67
    Activations Density 1.962%

    No Known Activations