© 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. 10-RES-JB
    11. 10526
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection and defense

    oai_token-act-pair · gpt-3.5-turbo

    references to protection and defense in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.60
     NEWS
    -0.60
    itcher
    -0.60
    starter
    -0.59
    acement
    -0.57
     modulation
    -0.57
    rossover
    -0.57
     QUEST
    -0.57
     mediation
    -0.56
     beginnings
    -0.56
    POSITIVE LOGITS
     against
    1.52
    against
    1.50
     Against
    1.24
     from
    0.93
     integrity
    0.92
    yrights
    0.85
     FROM
    0.85
     confidentiality
    0.84
    from
    0.82
    selves
    0.80
    Activations Density 0.167%

    No Known Activations