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. 9-RES-JB
    6. 9258
    Prev
    Next
    INDEX
    Explanations

    words related to violent or harsh actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and brutality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arten
    -0.79
    iasm
    -0.79
    ucket
    -0.75
    manuel
    -0.73
    kj
    -0.72
    glas
    -0.71
     Bundle
    -0.70
    bub
    -0.70
    conservancy
    -0.70
    leaf
    -0.69
    POSITIVE LOGITS
     punishments
    1.04
     cruelty
    0.96
     beasts
    0.92
     torture
    0.92
     murders
    0.91
     punishment
    0.91
     retribution
    0.91
     brutality
    0.88
     Slaughter
    0.87
     murder
    0.84
    Activations Density 0.107%

    No Known Activations