© 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. 10-RES-JB
    11. 12849
    Prev
    Next
    INDEX
    Explanations

    mentions of economic and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to economic systems and corporate involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clockwork
    -0.85
     Seconds
    -0.80
    Dialogue
    -0.78
    Anim
    -0.77
    ????????
    -0.77
    love
    -0.76
     Anniversary
    -0.74
    atoon
    -0.73
    ï¸ı
    -0.73
     anniversary
    -0.73
    POSITIVE LOGITS
     subsidy
    1.41
     subsid
    1.39
     taxed
    1.33
     subsidized
    1.33
     subsidies
    1.32
     incentiv
    1.31
     taxable
    1.28
     lucrative
    1.24
     monop
    1.22
     revenue
    1.21
    Activations Density 0.651%

    No Known Activations