Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 860
    Prev
    Next
    INDEX
    Explanations

    word sequences containing the verb "build"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "build" or variations thereof in various contexts

    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
    enance
    -0.81
    ighed
    -0.78
    oft
    -0.76
    ALT
    -0.73
    unknown
    -0.73
    inventoryQuantity
    -0.69
     Asked
    -0.68
    Ask
    -0.68
    tm
    -0.67
    Allow
    -0.67
    POSITIVE LOGITS
     new
    1.03
     makeshift
    0.97
     bunch
    0.96
     cohesive
    0.94
     coherent
    0.94
     believable
    0.93
     roadmap
    0.91
     composite
    0.89
     realistic
    0.87
     comprehensive
    0.87
    Activations Density 0.197%

    No Known Activations