© 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. 4-RES-JB
    11. 10704
    Prev
    Next
    INDEX
    Explanations

    numerical values related to averages

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate statistical averages or measures in various contexts

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

    No Comments

    Negative Logits
    cit
    -0.72
    nuts
    -0.71
    andro
    -0.71
    brew
    -0.70
    bane
    -0.70
    lean
    -0.68
    lez
    -0.68
    ading
    -0.68
    aina
    -0.66
    burg
    -0.65
    POSITIVE LOGITS
     hourly
    0.97
     monthly
    0.87
     yearly
    0.83
     estimate
    0.80
     GPA
    0.80
     daily
    0.79
     weekly
    0.79
     weekday
    0.79
     annual
    0.78
     rate
    0.78
    Activations Density 0.022%

    No Known Activations