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. 9-RES-JB
    6. 12786
    Prev
    Next
    INDEX
    Explanations

    terms related to user interaction, sign-up processes, and notifications

    oai_token-act-pair · gpt-3.5-turbo

    user account-related actions and statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    APS
    -0.63
    åħī
    -0.62
    ioned
    -0.60
    Eva
    -0.56
     frank
    -0.56
    Frank
    -0.56
    inis
    -0.56
    ecd
    -0.55
    entimes
    -0.55
    ongevity
    -0.55
    POSITIVE LOGITS
     hereby
    0.87
     browser
    0.86
     javascript
    0.79
     Login
    0.79
     Browser
    0.78
     Javascript
    0.74
     Password
    0.72
     guessed
    0.72
     JavaScript
    0.69
     requested
    0.69
    Activations Density 0.165%

    No Known Activations