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. 8-RES-JB
    6. 23981
    Prev
    Next
    INDEX
    Explanations

    text related to protection and security measures

    oai_token-act-pair · gpt-3.5-turbo

    the concept of protection in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hall
    -0.70
    jet
    -0.67
    LINE
    -0.64
    ANN
    -0.62
    LIN
    -0.62
    quartered
    -0.62
    Benz
    -0.61
     Fever
    -0.60
    Interstitial
    -0.59
    mad
    -0.58
    POSITIVE LOGITS
    ively
    1.14
    iveness
    1.03
     against
    0.99
    orate
    0.98
    against
    0.91
    ously
    0.91
    folios
    0.86
    atively
    0.85
    amental
    0.82
    icons
    0.80
    Activations Density 0.049%

    No Known Activations