© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2354
    Prev
    Next
    INDEX
    Explanations

    words related to drowning or overwhelming submersion

    oai_token-act-pair · gpt-3.5-turbo

    terms related to drowning or submersion in water

    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
    zag
    -0.72
     easing
    -0.68
    TeX
    -0.68
    WB
    -0.65
     permissions
    -0.65
    ################
    -0.63
    nec
    -0.62
    ORPG
    -0.60
     directives
    -0.60
    essler
    -0.60
    POSITIVE LOGITS
     drown
    0.98
     drowning
    0.94
     drowned
    0.85
     overboard
    0.80
     ashore
    0.80
     Squid
    0.79
    lings
    0.73
    stall
    0.71
    leneck
    0.70
     Innocent
    0.70
    Activations Density 0.036%

    No Known Activations