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. 1-RES-JB
    6. 16564
    Prev
    Next
    INDEX
    Explanations

    terms related to diversification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    occurrences related to the concept of diversification

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reloaded
    -0.86
    Fax
    -0.86
    TOP
    -0.84
    FUL
    -0.83
    UFF
    -0.78
    TX
    -0.73
    Madison
    -0.71
    ATCH
    -0.71
    ATA
    -0.70
    Wisconsin
    -0.68
    POSITIVE LOGITS
     divers
    1.50
     horizont
    1.12
    iversity
    1.00
    ifiers
    1.00
    ivers
    0.98
    emouth
    0.95
    icult
    0.95
    itionally
    0.91
    ifies
    0.89
    icion
    0.89
    Activations Density 0.005%

    No Known Activations