© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17081
    Prev
    Next
    INDEX
    Explanations

    words related to changes in quantities or proportions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "in" followed by numerical data or percentages

    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
    çīĪ
    -0.88
    fab
    -0.75
    fuck
    -0.75
    Planet
    -0.73
    aldi
    -0.72
    Sham
    -0.72
    leon
    -0.72
    »Ĵ
    -0.71
    spring
    -0.70
    woods
    -0.69
    POSITIVE LOGITS
     popularity
    1.14
    efficiency
    1.01
     incidence
    0.99
     productivity
    0.98
     activity
    0.96
     revenues
    0.95
     competitiveness
    0.90
     revenue
    0.90
     prevalence
    0.89
     profitability
    0.89
    Activations Density 0.096%

    No Known Activations