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. 6-RES-JB
    6. 24321
    Prev
    Next
    INDEX
    Explanations

    instructions or steps involving going to specific locations or websites

    oai_token-act-pair · gpt-3.5-turbo

    instructions or commands for users to follow

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wishes
    -0.69
     hurled
    -0.69
     wished
    -0.63
     evaluations
    -0.61
     teased
    -0.61
     graz
    -0.61
     hairc
    -0.60
     conveyed
    -0.60
    worth
    -0.60
     smiles
    -0.59
    POSITIVE LOGITS
     Lobby
    0.74
    addons
    0.71
    nda
    0.69
     Enlightenment
    0.69
     Ctrl
    0.69
     Gutenberg
    0.68
    grid
    0.68
    ebin
    0.66
     whichever
    0.66
     Settings
    0.65
    Activations Density 0.098%

    No Known Activations