© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7085
    Prev
    Next
    INDEX
    Explanations

    words related to diversification or variation

    oai_token-act-pair · gpt-3.5-turbo

    variations and forms of the word "diversify."

    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
    Reloaded
    -0.80
    Madison
    -0.70
    ³³³³³³³³³³³³³³³³
    -0.69
     Archdemon
    -0.69
    TOP
    -0.68
    Fax
    -0.68
    âĹ
    -0.63
    ATA
    -0.63
    TEXT
    -0.62
    JA
    -0.61
    POSITIVE LOGITS
    ified
    1.17
    ification
    1.14
    ifying
    1.13
    icult
    1.09
    ivers
    1.04
    ions
    1.00
    ities
    1.00
    ify
    0.99
    iversity
    0.98
    itionally
    0.97
    Activations Density 0.029%

    No Known Activations