© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 713
    Prev
    Next
    INDEX
    Explanations

    references to the snack food "Doritos"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dor."

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

    No Comments

    Negative Logits
    anwhile
    -0.89
    WAYS
    -0.75
     Terrorism
    -0.70
    unct
    -0.70
    tenance
    -0.65
    xual
    -0.64
    pmwiki
    -0.64
    BRE
    -0.62
    HS
    -0.62
     PATH
    -0.61
    POSITIVE LOGITS
    ÃŃa
    0.95
    ado
    0.95
    cas
    0.93
    je
    0.92
    oshenko
    0.92
    iane
    0.90
    rell
    0.88
    iac
    0.87
    rance
    0.85
    acies
    0.85
    Activations Density 0.008%

    No Known Activations