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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20264
    Prev
    Next
    INDEX
    Explanations

    instances where something is less compared to a standard, such as less money, less profit, or less rainfall

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to scarcity or abundance, particularly in economic and environmental contexts

    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
    wered
    -0.76
    osc
    -0.70
    ADRA
    -0.68
     unpre
    -0.66
    oufl
    -0.65
    iseum
    -0.63
     Beaut
    -0.61
    regon
    -0.61
     Gleaming
    -0.60
     Remastered
    -0.60
    POSITIVE LOGITS
     anymore
    0.96
     altogether
    0.94
     than
    0.89
     nor
    0.84
     (<
    0.82
     Than
    0.77
     compared
    0.71
    than
    0.70
     bother
    0.70
     overall
    0.68
    Activations Density 0.214%

    No Known Activations