© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    words related to a product or brand named "Ale"

    oai_token-act-pair · gpt-3.5-turbo

    references to "ale" in various contexts

    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
    nl
    -0.82
    nesses
    -0.77
     Beir
    -0.76
    ness
    -0.73
    staff
    -0.71
    soDeliveryDate
    -0.70
    ingen
    -0.67
    ulates
    -0.66
    olicy
    -0.61
    ENTION
    -0.61
    POSITIVE LOGITS
    cki
    1.09
    xit
    1.08
    uca
    0.98
    ppo
    0.91
    jandro
    0.88
    esi
    0.87
    lla
    0.85
    ttes
    0.83
    ibaba
    0.83
    ño
    0.81
    Activations Density 0.037%

    No Known Activations