© 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. 6-RES-JB
    11. 17155
    Prev
    Next
    INDEX
    Explanations

    references to the Green Bay Packers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Green."

    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
    orically
    -0.83
    nces
    -0.77
    Downloadha
    -0.75
    mble
    -0.71
    illation
    -0.71
    ebin
    -0.71
     sshd
    -0.70
    gerald
    -0.69
    ̶
    -0.69
    illery
    -0.68
    POSITIVE LOGITS
    grass
    1.14
    leaf
    1.06
    stuff
    0.93
    wich
    0.93
     Lantern
    0.89
    haven
    0.89
    house
    0.89
    baum
    0.88
    lee
    0.87
    field
    0.86
    Activations Density 0.017%

    No Known Activations