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

    words related to acts of violence or killing

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "slaughter."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ronaldo
    -0.64
     Ric
    -0.62
     Richards
    -0.61
     Crom
    -0.61
     Princ
    -0.60
     Sovereign
    -0.60
    Scot
    -0.60
    âĵĺ
    -0.59
     retention
    -0.59
    aucas
    -0.59
    POSITIVE LOGITS
     Slaughter
    1.17
     slaughter
    1.15
    houses
    1.08
    \\\\\\\\
    1.01
    edIn
    0.93
    ãĥ¼ãĤ¯
    0.92
    house
    0.91
    quished
    0.90
    fest
    0.88
     slaughtered
    0.84
    Activations Density 0.012%

    No Known Activations