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. 10-RES-JB
    6. 7561
    Prev
    Next
    INDEX
    Explanations

    buzzwords and phrases related to finance and economic trends

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating economic downturns or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.69
    unte
    -0.65
     donated
    -0.64
    Lic
    -0.61
    VICE
    -0.60
    Shop
    -0.60
    ricted
    -0.59
    Choice
    -0.58
    Stew
    -0.57
    license
    -0.57
    POSITIVE LOGITS
     exponential
    1.15
     phenomena
    1.13
     fluctuations
    1.13
     gradual
    1.09
     occurring
    1.07
     precip
    1.05
     cycles
    1.03
     trends
    1.02
     fluct
    1.02
     stagnation
    1.02
    Activations Density 1.200%

    No Known Activations