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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 7382
    Prev
    Next
    INDEX
    Explanations

    terms related to database authentication and security

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to authentication and security in databases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yards
    -0.81
    projects
    -0.75
    ¬¼
    -0.72
    eca
    -0.71
    improve
    -0.70
    å§«
    -0.70
    ŃĶ
    -0.69
    carb
    -0.69
     guiActiveUnfocused
    -0.67
    bilt
    -0.67
    POSITIVE LOGITS
     HTTP
    1.16
     encrypted
    1.15
     authentication
    1.15
     passwords
    1.10
     Authentication
    1.06
     SSL
    1.04
     password
    1.03
    encrypted
    0.99
     cryptographic
    0.99
     spoof
    0.98
    Activations Density 0.315%

    No Known Activations