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. 20145
    Prev
    Next
    INDEX
    Explanations

    references to the snack food item "Doritos"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name or entity, particularly involving "Dor."

    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
    anwhile
    -0.88
    WAYS
    -0.71
    BRE
    -0.67
    HS
    -0.67
    eers
    -0.64
     Terrorism
    -0.62
    testing
    -0.60
    ³³³³³³³³
    -0.60
     Continued
    -0.60
    Quotes
    -0.60
    POSITIVE LOGITS
    je
    0.95
    ado
    0.92
    ÃŃa
    0.89
    iane
    0.89
    omial
    0.85
    chester
    0.85
    acle
    0.85
    fman
    0.85
    izon
    0.84
    oshenko
    0.84
    Activations Density 0.016%

    No Known Activations