© 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. 6087
    Prev
    Next
    INDEX
    Explanations

    economic competition and business strategies

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

    business-related terms, such as company names and economic concepts

    oai_token-act-pair · gpt-3.5-turbo
    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
     Investigator
    -0.68
     tonight
    -0.67
     Diary
    -0.66
     Auschwitz
    -0.66
     Rape
    -0.64
     Observer
    -0.64
     Forensic
    -0.62
     Sergeant
    -0.62
     Yesterday
    -0.62
     Investigation
    -0.61
    POSITIVE LOGITS
     lucrative
    0.91
     theirs
    0.86
     niche
    0.83
     incumb
    0.82
     pricey
    0.79
     compete
    0.78
     competitors
    0.77
     monopol
    0.77
     budgets
    0.76
     costly
    0.74
    Activations Density 1.319%

    No Known Activations