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. 10-RES-JB
    6. 11671
    Prev
    Next
    INDEX
    Explanations

    salutations at the beginning of letters, especially ones directed towards specific people

    oai_token-act-pair · gpt-3.5-turbo

    the term "Dear" as it appears in correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioch
    -0.95
    ucket
    -0.75
    eal
    -0.74
    uits
    -0.74
    elson
    -0.72
    igsaw
    -0.71
    frac
    -0.70
    ember
    -0.70
    ilib
    -0.70
    osta
    -0.69
    POSITIVE LOGITS
     Reader
    1.42
     Readers
    1.27
     reader
    1.23
     readers
    1.15
     Friends
    1.08
     Diary
    1.06
     friends
    0.98
     Fellow
    0.95
     Leader
    0.93
     Editor
    0.91
    Activations Density 0.018%

    No Known Activations