Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7864
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition, fairness, safeguards, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fairness and competition in economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pleted
    -0.83
     Mour
    -0.77
    odiac
    -0.77
     Survivors
    -0.72
     Gork
    -0.72
     VICE
    -0.71
     condolences
    -0.70
     condol
    -0.67
    ocument
    -0.67
     Melania
    -0.67
    POSITIVE LOGITS
     monopol
    1.56
     monop
    1.56
     monopoly
    1.55
     antitrust
    1.50
     pricing
    1.49
     incentiv
    1.44
     disadvant
    1.42
     unfair
    1.39
     cartel
    1.37
     incentives
    1.35
    Activations Density 0.745%

    No Known Activations