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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18721
    Prev
    Next
    INDEX
    Explanations

    large quantities or numbers of items or people

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people or quantities

    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
    agate
    -0.77
     Redemption
    -0.70
    ãĥ¤
    -0.70
    iban
    -0.69
    clusively
    -0.69
    inventoryQuantity
    -0.67
    Interstitial
    -0.66
    Delivery
    -0.62
    mentioned
    -0.62
    Ħ¢
    -0.60
    POSITIVE LOGITS
    ourcing
    0.89
    ourced
    0.87
     ILCS
    0.87
     upon
    0.83
     of
    0.80
    aires
    0.80
    rd
    0.77
     worldwide
    0.74
     migrating
    0.70
     thousands
    0.69
    Activations Density 0.043%

    No Known Activations