© 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. 3955
    Prev
    Next
    INDEX
    Explanations

    instances where someone refuses to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "refused"

    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
    Clean
    -0.82
    groups
    -0.81
    psc
    -0.76
    Day
    -0.76
    Assembly
    -0.75
    è¦ļéĨĴ
    -0.75
    mental
    -0.74
    GROUP
    -0.73
    day
    -0.71
    arya
    -0.70
    POSITIVE LOGITS
     refused
    0.93
     refuse
    0.93
    ĸļ
    0.88
     refuses
    0.87
     vehemently
    0.84
     refusal
    0.80
     refusing
    0.80
     miser
    0.79
     repeatedly
    0.77
     unanimously
    0.74
    Activations Density 0.012%

    No Known Activations