© 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. 5367
    Prev
    Next
    INDEX
    Explanations

    phrases related to acts of rescue or saving

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of saving or rescue

    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
    yond
    -0.77
    RY
    -0.76
    quartered
    -0.76
    ounce
    -0.67
    KER
    -0.66
    NSA
    -0.62
     sclerosis
    -0.62
    Cola
    -0.62
     impressions
    -0.61
    VP
    -0.60
    POSITIVE LOGITS
    Save
    0.79
     hostages
    0.79
     souls
    0.77
     Lives
    0.76
     lives
    0.74
     rescue
    0.74
     Save
    0.73
     Sanctuary
    0.72
     mankind
    0.70
    save
    0.68
    Activations Density 0.051%

    No Known Activations