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. 10381
    Prev
    Next
    INDEX
    Explanations

    keywords related to cyber security and related topics

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cyber activities and cybersecurity

    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
     Strauss
    -0.81
    ered
    -0.79
    erer
    -0.74
     Clement
    -0.73
    IELD
    -0.71
    ained
    -0.70
    ++++++++++++++++
    -0.69
     guiActiveUnfocused
    -0.69
    ×ķ
    -0.68
    UCT
    -0.68
    POSITIVE LOGITS
    netic
    1.41
    punk
    1.03
    prus
    0.98
    security
    0.97
    ulent
    0.91
    attacks
    0.90
    nation
    0.89
    dimension
    0.88
    suit
    0.84
     Cyber
    0.83
    Activations Density 0.013%

    No Known Activations