© 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. 8608
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities and incidents

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or crime involving multiple individuals

    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
    isSpecialOrderable
    -0.89
    ãĤ´ãĥ³
    -0.82
    inventoryQuantity
    -0.76
     widest
    -0.68
    é¾įå¥ij士
    -0.67
    issance
    -0.65
    ":"/
    -0.64
     disclaimer
    -0.63
    ãĤ¦ãĤ¹
    -0.63
    TION
    -0.63
    POSITIVE LOGITS
     respectively
    1.20
    selves
    1.03
     together
    1.02
     collectively
    1.02
     apiece
    0.99
     themselves
    0.97
     jointly
    0.96
     conspiring
    0.87
     throats
    0.84
     kidnap
    0.84
    Activations Density 0.539%

    No Known Activations