© 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. 8-RES-JB
    11. 15158
    Prev
    Next
    INDEX
    Explanations

    phrases related to criticism or controversy

    oai_token-act-pair · gpt-3.5-turbo

    expressions of distrust and criticism towards authority or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellar
    -0.82
    restricted
    -0.78
    interrupted
    -0.78
    rapnel
    -0.74
    uttered
    -0.74
    orb
    -0.71
    iffe
    -0.68
    bott
    -0.65
    ocated
    -0.63
    oof
    -0.63
    POSITIVE LOGITS
     democracy
    0.97
     democratic
    0.90
     innocent
    0.87
     taxp
    0.87
     democratically
    0.86
     livelihood
    0.85
     legitimate
    0.85
     morals
    0.85
     dignity
    0.84
     credibility
    0.84
    Activations Density 0.803%

    No Known Activations