© 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. 8-RES-JB
    11. 7052
    Prev
    Next
    INDEX
    Explanations

    legal or law enforcement-related terms and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or criminal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.74
    eals
    -0.63
    itton
    -0.61
    ãĥ©ãĥ³
    -0.59
     majesty
    -0.57
    emn
    -0.56
    _-
    -0.56
    igl
    -0.55
    nutrition
    -0.55
    visors
    -0.54
    POSITIVE LOGITS
     whatsoever
    1.52
     nor
    1.35
     anymore
    1.17
    soever
    0.99
     anywhere
    0.97
     EVER
    0.90
    nor
    0.83
     ever
    0.78
     except
    0.78
     slightest
    0.75
    Activations Density 0.405%

    No Known Activations