© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5050
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection, security, and defense

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to protection and security for individuals, families, and communities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     mediation
    -0.68
    acement
    -0.62
     understatement
    -0.61
    Gov
    -0.60
    Discussion
    -0.60
    Enter
    -0.59
     persuasion
    -0.58
    Change
    -0.58
     ado
    -0.58
     QUEST
    -0.58
    POSITIVE LOGITS
     against
    1.53
    against
    1.51
     Against
    1.17
     from
    0.89
     interests
    0.88
    yrights
    0.84
     integrity
    0.83
    from
    0.82
     rights
    0.82
     privacy
    0.82
    Activations Density 0.280%

    No Known Activations