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. 12777
    Prev
    Next
    INDEX
    Explanations

    references to sexual assault

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual assault and related crimes

    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
    issue
    -0.81
    clips
    -0.81
    immune
    -0.75
    issues
    -0.75
    hire
    -0.72
    etheless
    -0.72
    rek
    -0.72
    edition
    -0.70
    lore
    -0.70
    fare
    -0.69
    POSITIVE LOGITS
     him
    0.87
     them
    0.73
     unsuspecting
    0.72
     prostitutes
    0.72
     himself
    0.70
     innoc
    0.67
     raping
    0.67
     Samantha
    0.65
     innocent
    0.65
     aggressively
    0.65
    Activations Density 0.083%

    No Known Activations