© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 4535
    Prev
    Next
    INDEX
    Explanations

    issues related to economics and finance

    oai_token-act-pair · gpt-3.5-turbo

    cumulative phrases indicating the state or condition of various issues

    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
    itar
    -0.75
     inquire
    -0.70
    itely
    -0.68
     Reach
    -0.61
    ####
    -0.61
    */
    -0.60
     Chosen
    -0.59
     Anniversary
    -0.59
    idav
    -0.58
    Original
    -0.57
    POSITIVE LOGITS
     causing
    1.45
     affecting
    1.39
     impacting
    1.38
     harming
    1.37
     forcing
    1.36
     disrupting
    1.36
     fueling
    1.34
     ruining
    1.34
     hurting
    1.32
     undermining
    1.31
    Activations Density 0.215%

    No Known Activations