Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23170
    Prev
    Next
    INDEX
    Explanations

    mentions of violent actions or tragic events

    oai_token-act-pair · gpt-3.5-turbo

    instances of violent actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.86
    natureconservancy
    -0.82
    dayName
    -0.79
    paren
    -0.78
    OTA
    -0.75
    Commerce
    -0.75
    leground
    -0.75
    peak
    -0.74
    tz
    -0.74
    CHAT
    -0.74
    POSITIVE LOGITS
     injuring
    1.16
     wounding
    1.06
     traumat
    1.00
     coroner
    0.98
     Luckily
    0.97
     inquest
    0.96
     survivors
    0.96
     injure
    0.95
     afterwards
    0.93
     assailants
    0.90
    Activations Density 0.585%

    No Known Activations