© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 154
    Prev
    Next
    INDEX
    Explanations

    sports teams and their current activities or status

    oai_token-act-pair · gpt-3.5-turbo

    present tense forms of the verb "to be" combined with indicators of team performance or status in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compan
    -0.75
     Rapp
    -0.72
    indust
    -0.71
     ministerial
    -0.70
    alyses
    -0.67
    activ
    -0.66
     panels
    -0.65
    ses
    -0.64
    compan
    -0.64
    lab
    -0.63
    POSITIVE LOGITS
     Playoff
    0.95
     preseason
    0.94
     dynasty
    0.89
     playoff
    0.89
     undefeated
    0.88
     offseason
    0.87
     unbeaten
    0.86
     relegation
    0.85
    QB
    0.84
     lineback
    0.84
    Activations Density 0.456%

    No Known Activations