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. 8-RES-JB
    6. 18951
    Prev
    Next
    INDEX
    Explanations

    words related to sports and gaming

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UID
    -0.78
    aye
    -0.75
    otte
    -0.74
    tein
    -0.67
    assi
    -0.65
    votes
    -0.64
    DoS
    -0.64
    Å¡
    -0.63
    rue
    -0.62
     Replacement
    -0.62
    POSITIVE LOGITS
     booming
    0.98
     genres
    0.98
     flourished
    0.94
     fascinated
    0.93
     flourishing
    0.87
    ateurs
    0.86
     niche
    0.83
     rife
    0.83
     genre
    0.83
     evolving
    0.82
    Activations Density 0.696%

    No Known Activations