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. 8630
    Prev
    Next
    INDEX
    Explanations

    terms related to authentication and security protocols

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to security and authentication in digital communication

    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
    hani
    -0.79
    improve
    -0.78
    ĸļ
    -0.77
    utenberg
    -0.77
    yards
    -0.77
    borough
    -0.75
     benches
    -0.74
    thur
    -0.73
     Hobby
    -0.71
    baugh
    -0.69
    POSITIVE LOGITS
     authentication
    1.13
     cryptographic
    1.07
     passwords
    1.07
     HTTP
    1.06
     encrypted
    1.06
     cryptography
    1.02
     password
    1.01
     handshake
    1.00
     Authentication
    0.99
     SSL
    0.99
    Activations Density 0.223%

    No Known Activations