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. 15369
    Prev
    Next
    INDEX
    Explanations

    sports events or tournaments associated with specific years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports events and seasons

    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
    iously
    -0.80
    onic
    -0.76
    uably
    -0.68
    iety
    -0.68
    dullah
    -0.67
    ious
    -0.67
    inventoryQuantity
    -0.67
    onite
    -0.62
    rity
    -0.62
    onian
    -0.62
    POSITIVE LOGITS
     festivities
    1.02
     finals
    0.80
     underway
    0.78
     lineup
    0.78
     slate
    0.77
     slated
    0.75
     celebrations
    0.75
     opener
    0.75
     countdown
    0.75
     airing
    0.74
    Activations Density 0.229%

    No Known Activations