© 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. 4819
    Prev
    Next
    INDEX
    Explanations

    information related to criminal investigations and law enforcement

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to law enforcement and investigative activities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    rawdownloadcloneembedreportprint
    -0.90
    ãĤ¦ãĤ¹
    -0.88
    ¥µ
    -0.76
    ò
    -0.74
    Translation
    -0.72
    ļéĨĴ
    -0.72
    ocide
    -0.72
    amental
    -0.71
    @@@@
    -0.71
    reads
    -0.70
    POSITIVE LOGITS
     allege
    1.22
     believe
    1.20
     say
    1.11
     searched
    1.03
     recovered
    1.02
     speculate
    1.01
     arrested
    0.98
     haven
    0.98
     suspect
    0.94
     aren
    0.92
    Activations Density 0.107%

    No Known Activations