© 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. 9-RES-JB
    11. 6923
    Prev
    Next
    INDEX
    Explanations

    descriptions of criminal activities and law enforcement efforts

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and crime-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anan
    -0.80
     Canal
    -0.77
    ikk
    -0.70
     Gems
    -0.70
     nutrit
    -0.69
    DERR
    -0.66
    Scot
    -0.66
     IU
    -0.65
    anty
    -0.64
     percentile
    -0.64
    POSITIVE LOGITS
     lurking
    1.03
     stalking
    1.03
     attacking
    0.95
     prow
    0.92
     undet
    0.92
     menacing
    0.92
     targeting
    0.90
     prey
    0.90
     terror
    0.90
     exploiting
    0.88
    Activations Density 0.915%

    No Known Activations