© 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. 9-RES-JB
    11. 3557
    Prev
    Next
    INDEX
    Explanations

    economic and policy-related terms and discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms associated with economic and financial implications

    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
    DragonMagazine
    -0.89
    assi
    -0.80
    ocular
    -0.71
     Fn
    -0.71
     subscript
    -0.70
     hier
    -0.67
    optional
    -0.66
     Freud
    -0.66
     disclaimer
    -0.66
    canon
    -0.65
    POSITIVE LOGITS
     affordability
    1.00
     economic
    1.00
    economic
    0.97
     prosperity
    0.95
    Economic
    0.95
     economically
    0.95
     businesses
    0.92
     incomes
    0.91
     economies
    0.90
     disadvantaged
    0.90
    Activations Density 0.539%

    No Known Activations