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. 10-RES-JB
    6. 7382
    Prev
    Next
    INDEX
    Explanations

    actions and events related to a sports match

    oai_token-act-pair · gpt-3.5-turbo

    key moments or events related to sports scoring and game sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tymology
    -0.86
    ombat
    -0.86
    soDeliveryDate
    -0.86
    soType
    -0.83
    TPP
    -0.82
    catentry
    -0.82
    ersive
    -0.81
    isodes
    -0.79
    Accessory
    -0.78
    uner
    -0.77
    POSITIVE LOGITS
     teammate
    1.15
     Rico
    1.12
     Devin
    1.10
     Nicolas
    1.09
     Kenny
    1.08
     Josh
    1.06
     Giov
    1.05
     Noel
    1.03
     Trey
    1.02
     Jar
    1.01
    Activations Density 0.166%

    No Known Activations