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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 7907
    Prev
    Next
    INDEX
    Explanations

    phrases related to violence and negative societal behaviors

    oai_token-act-pair · gpt-3.5-turbo

    topics related to violence and its various forms, including specific issues like crime, terrorism, and violence against marginalized groups

    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
    shire
    -0.95
    ortium
    -0.77
    ierre
    -0.73
    enium
    -0.70
    gio
    -0.70
    hower
    -0.69
    ource
    -0.68
     trustworthy
    -0.68
     fray
    -0.67
    ository
    -0.66
    POSITIVE LOGITS
    Ń·
    0.90
    icides
    0.83
    à¨
    0.75
    stad
    0.67
    Lyn
    0.66
    Pref
    0.65
    parts
    0.65
     inflicted
    0.64
    Usage
    0.64
     indiscrim
    0.63
    Activations Density 0.449%

    No Known Activations