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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7-RES-JB
    6. 2579
    Prev
    Next
    INDEX
    Explanations

    words related to diversity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of diversity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.73
    çͰ
    -0.70
    WARD
    -0.69
    keeper
    -0.67
    rollers
    -0.66
    rol
    -0.64
    oldown
    -0.64
     guaranteeing
    -0.64
    Pass
    -0.64
    Roy
    -0.63
    POSITIVE LOGITS
     assemb
    0.96
    ively
    0.92
    ortment
    0.90
    iveness
    0.89
     perspectives
    0.88
     viewpoints
    0.88
    mble
    0.87
    iterranean
    0.83
    iated
    0.83
    iating
    0.83
    Activations Density 0.036%

    No Known Activations