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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 15161
    Prev
    Next
    INDEX
    Explanations

    information related to sports news, specifically regarding team activities and player changes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports team dynamics and player performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    conom
    -0.95
    hiba
    -0.80
    tif
    -0.78
    atra
    -0.74
    Bloomberg
    -0.73
    ICES
    -0.69
    lations
    -0.69
    akov
    -0.64
    AFTA
    -0.64
    åĪ
    -0.64
    POSITIVE LOGITS
     mascot
    1.13
     superstar
    1.11
     marquee
    1.10
     bye
    1.10
     logo
    0.94
     ace
    0.94
     leader
    0.93
     roster
    0.91
     lineup
    0.89
     star
    0.89
    Activations Density 0.253%

    No Known Activations