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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 1546
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific sports teams, particularly the Green Bay Packers

    oai_token-act-pair · gpt-3.5-turbo

    references to the Green Bay Packers sports team

    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
     concess
    -0.81
    schild
    -0.74
     MH
    -0.73
    accompanied
    -0.73
    rez
    -0.72
    Austral
    -0.72
    isSpecialOrderable
    -0.67
    cur
    -0.67
     nep
    -0.63
     complimentary
    -0.61
    POSITIVE LOGITS
    veland
    0.83
     Packers
    0.83
     Tribe
    0.77
     Athletic
    0.77
    vation
    0.72
     Warriors
    0.72
     Athletics
    0.71
     Utilities
    0.70
    ffen
    0.70
    ¯¯
    0.69
    Activations Density 0.031%

    No Known Activations