© 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. 6-RES-JB
    11. 499
    Prev
    Next
    INDEX
    Explanations

    instances of people lying down or collapsing in various scenarios

    oai_token-act-pair · gpt-3.5-turbo

    instances of individuals in vulnerable or compromised physical states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.75
     Cosponsors
    -0.69
    invoke
    -0.68
    İ
    -0.68
    alty
    -0.67
     Blazing
    -0.66
     Voters
    -0.64
     Generation
    -0.63
     specialization
    -0.63
    Ĥª
    -0.62
    POSITIVE LOGITS
     slumped
    0.96
     asleep
    0.96
     lifeless
    0.92
     crou
    0.90
     limp
    0.89
     unconscious
    0.86
     upright
    0.81
     beside
    0.80
     knees
    0.80
     prone
    0.78
    Activations Density 0.230%

    No Known Activations