© 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. 2-RES-JB
    11. 10451
    Prev
    Next
    INDEX
    Explanations

    names of individuals with a relationship context, presumably looking for mentions of partners

    oai_token-act-pair · gpt-3.5-turbo

    references to partnerships or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aston
    -0.79
    anism
    -0.73
    cale
    -0.71
    ouses
    -0.67
    iard
    -0.67
    aji
    -0.67
    printed
    -0.66
    sa
    -0.66
     actionGroup
    -0.65
    asty
    -0.65
    POSITIVE LOGITS
     partner
    1.29
     partners
    1.05
     Partner
    1.00
     colleague
    0.77
     competitor
    0.77
    ãĤ´ãĥ³
    0.77
    loo
    0.72
     collaborator
    0.71
     Karin
    0.68
    âĸ¬âĸ¬
    0.68
    Activations Density 0.012%

    No Known Activations