© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20068
    Prev
    Next
    INDEX
    Explanations

    words related to suicide

    oai_token-act-pair · gpt-3.5-turbo

    words related to suicide and self-harm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     directions
    -0.81
     Turks
    -0.73
     Fathers
    -0.67
     tightening
    -0.66
     gasoline
    -0.63
     Lyme
    -0.63
     Gutenberg
    -0.63
     torque
    -0.62
    heads
    -0.62
     earnest
    -0.61
    POSITIVE LOGITS
    zanne
    1.28
    arez
    1.28
    icide
    1.17
    pper
    1.08
    ply
    1.04
    su
    1.03
    icides
    1.02
    itable
    1.02
    itton
    1.02
    pped
    1.01
    Activations Density 0.012%

    No Known Activations