© 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. 22826
    Prev
    Next
    INDEX
    Explanations

    sentences related to national economic issues, such as defaulting on payments or joining monetary unions

    oai_token-act-pair · gpt-3.5-turbo

    topics discussing economic uncertainty and political dynamics related to the European Union and Greece

    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
     predictive
    -0.71
     anecdotes
    -0.68
     Insp
    -0.67
    pain
    -0.66
     motivational
    -0.65
     Investigations
    -0.65
     sarc
    -0.65
     comforting
    -0.64
     Painter
    -0.64
     Detect
    -0.64
    POSITIVE LOGITS
     annexed
    1.23
     annex
    1.06
     capit
    1.04
     secession
    1.04
    ndum
    1.01
     unilaterally
    1.00
     independence
    0.97
     withdraw
    0.94
     revert
    0.94
     become
    0.92
    Activations Density 0.465%

    No Known Activations