© 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. 2-RES-JB
    11. 4175
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refusal"

    oai_token-act-pair · gpt-3.5-turbo

    instances of refusal or inability to comply with requests or demands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icle
    -0.77
    agog
    -0.72
    icles
    -0.71
    aum
    -0.70
    umm
    -0.69
    estones
    -0.67
    nesium
    -0.66
     Clancy
    -0.66
    osh
    -0.65
    amaz
    -0.63
    POSITIVE LOGITS
     refusal
    0.99
     unwillingness
    0.96
    yip
    0.93
     reversal
    0.90
     reliance
    0.89
     compulsion
    0.88
     adherence
    0.86
     aversion
    0.84
     hesitation
    0.83
     stance
    0.83
    Activations Density 0.034%

    No Known Activations