© 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. 7-RES-JB
    11. 12419
    Prev
    Next
    INDEX
    Explanations

    references to situations where someone's life is in danger or threatened

    oai_token-act-pair · gpt-3.5-turbo

    references to life-threatening situations or the concept of life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Celest
    -0.77
    ERC
    -0.72
     Compliance
    -0.71
    Hyper
    -0.69
    channelAvailability
    -0.68
    xual
    -0.66
     CES
    -0.64
     propri
    -0.64
    lav
    -0.64
    é¾įåĸļ士
    -0.64
    POSITIVE LOGITS
    guards
    1.14
    boats
    1.10
    boat
    1.02
    killers
    0.96
    mares
    0.95
    ously
    0.89
    guard
    0.89
    lihood
    0.88
    ffen
    0.87
     slain
    0.85
    Activations Density 0.053%

    No Known Activations