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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 19183
    Prev
    Next
    INDEX
    Explanations

    information related to sports players and their playing careers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "play" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortium
    -0.69
    imb
    -0.68
    cult
    -0.68
    thening
    -0.66
    intestinal
    -0.65
    utter
    -0.64
    perial
    -0.62
    brow
    -0.62
    heric
    -0.62
    pora
    -0.61
    POSITIVE LOGITS
    wright
    0.97
     played
    0.94
    ername
    0.92
     Played
    0.88
     Plays
    0.84
    plays
    0.83
    Ò
    0.78
    imony
    0.77
    lists
    0.76
     Piano
    0.76
    Activations Density 0.053%

    No Known Activations