© 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
    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. 12534
    Prev
    Next
    INDEX
    Explanations

    adjectives related to economic conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic weakness and decline

    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
     unconsciously
    -0.78
    udder
    -0.76
     unknow
    -0.74
     casually
    -0.73
    ften
    -0.71
     unwittingly
    -0.69
     awkwardly
    -0.68
     redacted
    -0.68
     consciously
    -0.68
     arrog
    -0.68
    POSITIVE LOGITS
     finances
    1.14
     economy
    1.09
     economic
    1.05
     economies
    1.05
     revenues
    1.04
     earnings
    1.03
     turnout
    1.03
     rainfall
    1.02
     demographics
    1.01
     wages
    1.01
    Activations Density 0.172%

    No Known Activations