© 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. 8-RES-JB
    11. 4310
    Prev
    Next
    INDEX
    Explanations

    mentions of specific soda brands, mainly Pepsi and Coca-Cola

    oai_token-act-pair · gpt-3.5-turbo

    mentions of popular beverage brands, particularly Pepsi and Coca-Cola

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ailable
    -0.94
    ancial
    -0.81
    aldo
    -0.77
    guards
    -0.76
    HCR
    -0.74
    ittance
    -0.71
    ounding
    -0.71
    comed
    -0.70
    existent
    -0.67
    adows
    -0.67
    POSITIVE LOGITS
    Cola
    1.40
     Bottle
    1.03
     Coke
    0.99
    Mobil
    0.98
     Coca
    0.97
     Clicker
    0.92
     Mobil
    0.89
    Bott
    0.88
     Pepsi
    0.86
     bottle
    0.83
    Activations Density 0.064%

    No Known Activations