© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1336
    Prev
    Next
    INDEX
    Explanations

    relationships or interactions between people such as friends, colleagues, buyers, and spectators

    oai_token-act-pair · gpt-3.5-turbo

    references to people and their relationships to others

    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
     VIDEOS
    -0.79
     Pieces
    -0.73
     Dragonbound
    -0.73
    brids
    -0.71
     ACTIONS
    -0.69
     instruments
    -0.69
     Monsters
    -0.68
    adders
    -0.67
    ptions
    -0.67
    MEN
    -0.67
    POSITIVE LOGITS
     named
    1.52
     who
    1.32
     whom
    1.30
     whose
    1.24
     surn
    1.15
     nicknamed
    1.12
    who
    1.00
    whose
    0.99
    friend
    0.96
     friend
    0.94
    Activations Density 0.234%

    No Known Activations