© 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. 23771
    Prev
    Next
    INDEX
    Explanations

    financial terms and indicators

    oai_token-act-pair · gpt-3.5-turbo

    financial stability and growth indicators in economic contexts

    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
     proble
    -0.73
     cumbers
    -0.64
     gul
    -0.64
     destro
    -0.63
     manufact
    -0.61
     idiot
    -0.60
    iquette
    -0.60
     Innocent
    -0.60
    guyen
    -0.60
     bribe
    -0.59
    POSITIVE LOGITS
     amid
    0.95
     (+
    0.92
    luster
    0.92
     despite
    0.90
    daq
    0.88
     (-
    0.86
     compared
    0.86
     nationally
    0.86
    despite
    0.85
     domestically
    0.85
    Activations Density 0.268%

    No Known Activations