© 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. 6-RES-JB
    11. 17820
    Prev
    Next
    INDEX
    Explanations

    medical conditions or events that are life-threatening

    oai_token-act-pair · gpt-3.5-turbo

    references to life-threatening situations or events

    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
    ulhu
    -0.94
     Cree
    -0.77
     Carnegie
    -0.76
    ño
    -0.73
    etsk
    -0.71
    aco
    -0.70
    »Ĵ
    -0.70
     Ell
    -0.68
     Mock
    -0.68
    BLIC
    -0.67
    POSITIVE LOGITS
    saving
    1.22
    cycles
    0.95
    sized
    0.94
    cycle
    0.93
    wreck
    0.92
    oriented
    0.91
    eating
    0.91
    changing
    0.90
    consuming
    0.90
    tested
    0.89
    Activations Density 0.046%

    No Known Activations