© 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. 0-RES-JB
    11. 1728
    Prev
    Next
    INDEX
    Explanations

    words related to rivalry or competition

    oai_token-act-pair · gpt-3.5-turbo

    words related to rivalries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Agent
    -0.64
     effective
    -0.62
     agent
    -0.61
     underwater
    -0.60
     Auditor
    -0.59
     interactive
    -0.59
     MP
    -0.59
     proxy
    -0.58
     monet
    -0.58
     grammar
    -0.58
    POSITIVE LOGITS
    ries
    4.83
    ried
    2.49
    ry
    2.23
    rying
    2.20
    reys
    1.86
    rys
    1.76
    rie
    1.64
    RY
    1.62
    riers
    1.59
    rier
    1.53
    Activations Density 0.008%

    No Known Activations