© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 1851
    Prev
    Next
    INDEX
    Explanations

    words related to suicide

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "su" and its variations, indicating a focus on suicides or suicide-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     directions
    -0.74
     Gutenberg
    -0.74
     Lyme
    -0.70
     Turks
    -0.69
    heads
    -0.67
     STL
    -0.64
    artisan
    -0.64
     Orbit
    -0.64
    head
    -0.62
     Ashton
    -0.60
    POSITIVE LOGITS
    arez
    1.31
    zanne
    1.27
    icide
    1.21
    pper
    1.15
    icides
    1.13
    icidal
    1.08
    pport
    1.06
    perm
    1.06
    itable
    1.05
    pped
    1.00
    Activations Density 0.011%

    No Known Activations