© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17382
    Prev
    Next
    INDEX
    Explanations

    words related to hosting sports events

    oai_token-act-pair · gpt-3.5-turbo

    references to sports events and match outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compan
    -0.88
    awi
    -0.78
     manifold
    -0.75
     concess
    -0.74
    atography
    -0.72
    Companies
    -0.71
     modelling
    -0.71
    uters
    -0.70
    onomic
    -0.69
    lear
    -0.68
    POSITIVE LOGITS
     playoff
    1.15
     undefeated
    1.12
     unbeaten
    1.11
     playoffs
    1.02
     Finals
    1.01
     MVP
    0.96
     streak
    0.95
     Playoffs
    0.93
     rematch
    0.93
     semifinals
    0.92
    Activations Density 0.464%

    No Known Activations