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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 17410
    Prev
    Next
    INDEX
    Explanations

    privacy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to privacy and security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -0.82
    leys
    -0.80
    kell
    -0.79
    gling
    -0.74
     Mead
    -0.71
    iggs
    -0.71
    uana
    -0.71
    naire
    -0.69
     Kear
    -0.67
    gran
    -0.65
    POSITIVE LOGITS
    Privacy
    0.84
     privacy
    0.83
     preferences
    0.82
     preference
    0.79
    iframe
    0.78
     actionGroup
    0.73
     inbox
    0.71
     email
    0.70
     alert
    0.70
    policy
    0.70
    Activations Density 0.007%

    No Known Activations