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. 4026
    Prev
    Next
    INDEX
    Explanations

    references to written communication such as letters or requests

    oai_token-act-pair · gpt-3.5-turbo

    references to formal written communications, especially letters

    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
    illon
    -0.61
     deform
    -0.61
    ptions
    -0.60
    Variable
    -0.60
    onut
    -0.59
    Ħ¢
    -0.59
     å¤
    -0.59
    illian
    -0.59
    ivably
    -0.58
     Bronze
    -0.57
    POSITIVE LOGITS
     addressed
    1.05
     letter
    1.03
     dated
    1.00
     outlining
    0.99
    Letter
    0.95
     urging
    0.94
     inbox
    0.92
    letter
    0.91
     requesting
    0.91
     sent
    0.87
    Activations Density 0.107%

    No Known Activations