© 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. 9-RES-JB
    11. 5379
    Prev
    Next
    INDEX
    Explanations

    phrases related to market trends and sales figures

    oai_token-act-pair · gpt-3.5-turbo

    information related to sales and download statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constitutional
    -0.85
     archae
    -0.80
     Chomsky
    -0.78
    constitutional
    -0.76
     anthrop
    -0.74
     anat
    -0.73
     bureaucr
    -0.71
     interrogation
    -0.69
     fluor
    -0.69
     militar
    -0.69
    POSITIVE LOGITS
     Customers
    1.03
     subscriptions
    1.01
     customers
    1.01
     subscribers
    1.00
    Sales
    0.99
    Demand
    0.99
     retailers
    0.98
     subscriber
    0.98
     shipments
    0.96
     pricing
    0.92
    Activations Density 1.350%

    No Known Activations