© 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. 10-RES-JB
    11. 7753
    Prev
    Next
    INDEX
    Explanations

    actions and interactions in a dialogue

    oai_token-act-pair · gpt-3.5-turbo

    emotional expressions and interactions among characters

    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
     helicop
    -0.95
     freight
    -0.83
    espie
    -0.81
     golf
    -0.80
     Philly
    -0.77
     credential
    -0.76
     lockout
    -0.74
     galvan
    -0.73
     rigs
    -0.73
     treadmill
    -0.72
    POSITIVE LOGITS
    ãĢĮ
    1.68
    ãĢİ
    1.57
    âĶĢâĶĢ
    1.56
     ãĢĮ
    1.45
    ãĢIJ
    1.45
    ãĢį
    1.36
    ãĢı
    1.35
    âĹ
    1.33
     Sakuya
    1.32
    ãĢ
    1.28
    Activations Density 0.306%

    No Known Activations