© 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
    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. 12078
    Prev
    Next
    INDEX
    Explanations

    terms related to diversification

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "divers" and related terms in various contexts

    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
    walker
    -0.78
    pring
    -0.71
    appa
    -0.70
    ipped
    -0.68
    apo
    -0.68
    ername
    -0.67
     Wrath
    -0.65
     Rage
    -0.65
    ito
    -0.65
     disapproval
    -0.63
    POSITIVE LOGITS
     divers
    4.31
     diver
    1.50
     Diver
    1.31
     diversity
    1.19
     diverse
    1.16
     dive
    1.11
     diving
    1.09
     dives
    1.09
     hed
    1.08
    ivers
    1.06
    Activations Density 0.013%

    No Known Activations