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. 200
    Prev
    Next
    INDEX
    Explanations

    violent actions involving physical harm done by multiple individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and assault

    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
     clarity
    -0.70
    iences
    -0.70
    ournals
    -0.68
    phrine
    -0.66
    iae
    -0.66
    Bridge
    -0.65
    appiness
    -0.64
    ometer
    -0.64
    climate
    -0.63
    rums
    -0.61
    POSITIVE LOGITS
     swoop
    0.99
     harassing
    0.97
     mischief
    0.93
     stalking
    0.92
     extortion
    0.90
     hij
    0.89
     menacing
    0.89
     brazen
    0.88
     imperson
    0.88
     spree
    0.87
    Activations Density 1.008%

    No Known Activations