© 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. 13894
    Prev
    Next
    INDEX
    Explanations

    legal terms related to criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to possession and distribution of illegal substances or contraband

    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
    htt
    -0.71
     condol
    -0.70
    MQ
    -0.65
    Reply
    -0.64
    response
    -0.63
     subcontract
    -0.63
    ventures
    -0.60
     Zeit
    -0.60
     resc
    -0.60
     PsyNet
    -0.59
    POSITIVE LOGITS
     possession
    0.95
     possessed
    0.90
    holding
    0.87
    alogue
    0.83
     thereof
    0.82
     possessing
    0.79
    ivity
    0.77
    idable
    0.77
    ership
    0.75
    ivated
    0.72
    Activations Density 0.037%

    No Known Activations