© 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. 7-RES-JB
    11. 13855
    Prev
    Next
    INDEX
    Explanations

    instances where authorities conduct searches or raids

    oai_token-act-pair · gpt-3.5-turbo

    references to law enforcement actions, particularly searches and raids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cair
    -0.76
    reprene
    -0.75
    itis
    -0.71
    ankind
    -0.70
    terness
    -0.70
    adjust
    -0.69
    leness
    -0.67
    olf
    -0.67
     mastered
    -0.67
    ukemia
    -0.67
    POSITIVE LOGITS
     warrants
    0.97
     suspects
    0.93
     Manafort
    0.91
     warrant
    0.90
     premises
    0.90
     suspect
    0.87
     seizure
    0.86
     confiscated
    0.85
     affidavit
    0.81
     forfeiture
    0.81
    Activations Density 0.225%

    No Known Activations