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. 6-RES-JB
    6. 6128
    Prev
    Next
    INDEX
    Explanations

    phrases introducing a quote or piece of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases starting with "Here’s" followed by additional context or information

    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
    aneers
    -0.70
    ibles
    -0.70
    ange
    -0.69
    cair
    -0.68
    hate
    -0.67
     headaches
    -0.63
    esm
    -0.62
    aceutical
    -0.61
    iosity
    -0.61
     extermination
    -0.60
    POSITIVE LOGITS
     hoping
    0.82
     illustrate
    0.71
     excerpt
    0.65
     example
    0.65
     highlights
    0.64
     why
    0.63
     yours
    0.63
     Demo
    0.63
     snippet
    0.62
     courtesy
    0.61
    Activations Density 0.056%

    No Known Activations