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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 3520
    Prev
    Next
    INDEX
    Explanations

    phrases indicating impossibility or prohibition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express inability or restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ancer
    -0.65
    casting
    -0.65
     Generation
    -0.65
     Five
    -0.63
    liter
    -0.62
    bats
    -0.62
    ieu
    -0.61
    offs
    -0.60
     Loaded
    -0.60
    pocket
    -0.59
    POSITIVE LOGITS
    ĸļ
    1.11
     reproduce
    0.89
     necessarily
    0.88
     afford
    0.87
    adian
    0.86
    berra
    0.85
    't
    0.85
     exceed
    0.83
     attest
    0.80
     Canaver
    0.79
    Activations Density 0.020%

    No Known Activations