© 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. 11-RES-JB
    11. 898
    Prev
    Next
    INDEX
    Explanations

    personal letters starting with "Dear"

    oai_token-act-pair · gpt-3.5-turbo

    the salutation "Dear" in letters or correspondence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILS
    -0.76
    ioch
    -0.76
    -|
    -0.74
    ucket
    -0.72
    chery
    -0.69
     rife
    -0.68
    Closure
    -0.68
    âĶĢâĶĢ
    -0.67
    eal
    -0.66
     toget
    -0.65
    POSITIVE LOGITS
     Reader
    1.30
     Diary
    1.17
     Readers
    1.16
     reader
    1.02
     Editor
    0.97
     Abby
    0.95
     Leader
    0.95
     Friends
    0.94
     Customers
    0.94
     Neighbor
    0.93
    Activations Density 0.040%

    No Known Activations