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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 17801
    Prev
    Next
    INDEX
    Explanations

    words related to sports officiating and evaluations

    oai_token-act-pair · gpt-3.5-turbo

    references to officiating, referees, and review processes in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chin
    -0.99
    ILA
    -0.96
    byn
    -0.95
    bara
    -0.91
    Eva
    -0.90
    INTON
    -0.87
    Progress
    -0.83
    esson
    -0.77
    opian
    -0.77
    ricia
    -0.76
    POSITIVE LOGITS
     jerseys
    1.22
     announ
    1.20
     referees
    1.14
     announcer
    1.10
     leagues
    1.08
     coach
    1.07
     replay
    1.06
     coaches
    1.06
     jersey
    1.05
     scoreboard
    1.04
    Activations Density 0.276%

    No Known Activations