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. 0-RES-JB
    6. 4392
    Prev
    Next
    INDEX
    Explanations

    words related to physical acts of violence, particularly stabbing

    oai_token-act-pair · gpt-3.5-turbo

    references to stabbing or related violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Aut
    -0.69
    ICO
    -0.69
    je
    -0.67
     bott
    -0.66
     remed
    -0.65
     Model
    -0.65
     cloud
    -0.64
     Resources
    -0.62
     Review
    -0.61
    ans
    -0.61
    POSITIVE LOGITS
     stabbing
    3.01
     stabbed
    2.99
     stab
    2.85
    stab
    1.84
     Stab
    1.56
     decap
    1.37
     knife
    1.35
     knives
    1.32
     dagger
    1.30
     Knife
    1.17
    Activations Density 0.031%

    No Known Activations