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. 0-RES-JB
    6. 5505
    Prev
    Next
    INDEX
    Explanations

    names related to Kevin Garnett

    oai_token-act-pair · gpt-3.5-turbo

    references to specific players and their achievements in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fein
    -0.72
     Huck
    -0.72
     ko
    -0.72
    hiro
    -0.71
    EE
    -0.70
    pei
    -0.70
     Tunnel
    -0.69
    udo
    -0.69
    ians
    -0.68
     PW
    -0.67
    POSITIVE LOGITS
     Garn
    1.75
     Bou
    1.40
    Smith
    1.39
     compliment
    1.32
     Garland
    1.29
     scorer
    1.21
     compliments
    1.14
     additions
    1.08
     Shea
    0.98
    atron
    0.97
    Activations Density 0.031%

    No Known Activations