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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3372
    Prev
    Next
    INDEX
    Explanations

    salutations or greetings in a formal letter

    oai_token-act-pair · gpt-3.5-turbo

    repetitive salutations or address lines in letters

    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
    ioch
    -0.83
    elson
    -0.79
    orama
    -0.75
    ARC
    -0.69
    ember
    -0.69
    ucket
    -0.68
    eal
    -0.66
    onom
    -0.65
     foss
    -0.65
    osta
    -0.65
    POSITIVE LOGITS
     Reader
    0.87
     reader
    0.82
     Diary
    0.81
    born
    0.78
    iors
    0.77
    ths
    0.75
     Esther
    0.73
     Mama
    0.72
     Dear
    0.72
     Abby
    0.71
    Activations Density 0.037%

    No Known Activations