© 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. 9-RES-JB
    11. 12746
    Prev
    Next
    INDEX
    Explanations

    The neuron is specifically looking for terms related to categories

    oai_token-act-pair · gpt-3.5-turbo

    references to different categories or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bats
    -0.94
    ippi
    -0.74
     Zimmer
    -0.69
     Tuls
    -0.62
    kj
    -0.61
    zin
    -0.61
     Lauder
    -0.61
     Tycoon
    -0.59
     Tavern
    -0.58
    pter
    -0.58
    POSITIVE LOGITS
    naire
    0.89
    ifier
    0.84
     categories
    0.79
    category
    0.75
    ality
    0.74
    Category
    0.71
    ifiers
    0.70
     Categories
    0.69
    oola
    0.69
     category
    0.68
    Activations Density 0.031%

    No Known Activations