© 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. 17610
    Prev
    Next
    INDEX
    Explanations

    survivors of various types of hardship, trauma, or abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to survivors of trauma or abuse

    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
    sterdam
    -0.78
    ueller
    -0.74
    headed
    -0.72
    matically
    -0.68
    bledon
    -0.65
     busiest
    -0.65
    rams
    -0.64
    owler
    -0.64
    otom
    -0.63
    lay
    -0.62
    POSITIVE LOGITS
     Survivors
    0.94
     survivors
    0.93
     Survive
    0.85
     testimonies
    0.84
    Surv
    0.84
     survivor
    0.81
     Surviv
    0.80
     Survivor
    0.79
     crabs
    0.77
    surv
    0.76
    Activations Density 0.026%

    No Known Activations