Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 6491
    Prev
    Next
    INDEX
    Explanations

    keywords related to sports teams, matchups, and rankings

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports events and team standings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     apologise
    -1.00
     Whilst
    -0.99
     behaviours
    -0.95
     paed
    -0.92
     util
    -0.88
     behavioural
    -0.87
     organis
    -0.84
     whilst
    -0.81
     colourful
    -0.81
     behaviour
    -0.81
    POSITIVE LOGITS
     playoff
    1.33
     matchup
    1.26
     Playoff
    1.24
     matchups
    1.22
     postseason
    1.20
     undefeated
    1.14
     playoffs
    1.08
     wins
    1.06
     bye
    1.06
     rematch
    1.03
    Activations Density 0.594%

    No Known Activations