© 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. 11-RES-JB
    11. 17317
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection and safeguarding

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing protection or safeguarding against various threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -0.84
    ppa
    -0.81
    miah
    -0.81
    iken
    -0.77
    ynes
    -0.77
    arity
    -0.77
    arse
    -0.76
    unny
    -0.75
    ffe
    -0.73
    yy
    -0.71
    POSITIVE LOGITS
     predators
    1.08
     impending
    1.08
     harm
    1.07
     intrusion
    1.01
     exploitation
    0.99
     imminent
    0.99
     dangers
    0.98
     attackers
    0.97
     attacks
    0.97
     undue
    0.97
    Activations Density 0.122%

    No Known Activations