© 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. 7829
    Prev
    Next
    INDEX
    Explanations

    references to diversity

    oai_token-act-pair · gpt-3.5-turbo

    references to diversity in populations or groups

    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
    çĶ°
    -0.79
    ovember
    -0.72
    /+
    -0.71
    rollers
    -0.71
    Pass
    -0.70
    Ľ
    -0.69
    acher
    -0.69
    oldown
    -0.68
    ¤
    -0.66
     Annotations
    -0.66
    POSITIVE LOGITS
    ively
    0.98
     viewpoints
    0.97
     assemb
    0.95
     perspectives
    0.94
     array
    0.94
     assortment
    0.93
     cultures
    0.89
     personalities
    0.88
     populations
    0.87
     backgrounds
    0.87
    Activations Density 0.090%

    No Known Activations