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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10922
    Prev
    Next
    INDEX
    Explanations

    phrases related to violent acts, such as "slaughter."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "slaughter" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.75
    DCS
    -0.72
    ioxide
    -0.68
     fortun
    -0.68
    âĵĺ
    -0.63
    verage
    -0.61
    ency
    -0.61
    aucas
    -0.60
    annis
    -0.60
    rouse
    -0.58
    POSITIVE LOGITS
    houses
    1.16
     Slaughter
    1.14
    house
    0.98
    ificial
    0.88
     slaughter
    0.87
    hide
    0.85
    hammer
    0.85
    ãĥ¼ãĤ¯
    0.81
    birds
    0.81
     slaughtered
    0.81
    Activations Density 0.028%

    No Known Activations