© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17079
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to dangerous or life-threatening situations

    oai_token-act-pair · gpt-3.5-turbo

    references to lethal situations or actions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    acular
    -0.83
    angles
    -0.82
    roo
    -0.77
    rix
    -0.76
    hew
    -0.74
    arest
    -0.73
    romy
    -0.70
    Rate
    -0.69
    ramid
    -0.69
    IJ
    -0.68
    POSITIVE LOGITS
     injection
    1.04
     lethal
    0.99
    otine
    0.92
     injections
    0.84
    etheless
    0.83
    lethal
    0.82
    espie
    0.81
     dose
    0.81
    iza
    0.77
    ciating
    0.77
    Activations Density 0.009%

    No Known Activations