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. 19789
    Prev
    Next
    INDEX
    Explanations

    references to sports teams or individuals associated with the name "Tiger"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Tiger" and related entities, particularly in a sports or team context

    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
    ibel
    -0.74
    atform
    -0.74
    SOURCE
    -0.72
     Lennon
    -0.62
    iot
    -0.61
     Pastebin
    -0.61
     Geek
    -0.60
     Guatem
    -0.59
    rote
    -0.59
    iotic
    -0.59
    POSITIVE LOGITS
     Woods
    1.10
     Tigers
    1.03
     Tiger
    0.92
    bol
    0.86
    emonium
    0.81
    opard
    0.77
     tiger
    0.75
    lane
    0.74
     stripes
    0.74
    ures
    0.73
    Activations Density 0.044%

    No Known Activations