© 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. 23732
    Prev
    Next
    INDEX
    Explanations

    words related to financial and economic conditions, such as "stock prices," "housing data," and "tighter credit conditions."

    oai_token-act-pair · gpt-3.5-turbo

    economic indicators and factors affecting financial markets

    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
     ATT
    -0.68
    CI
    -0.65
    Lear
    -0.61
    ione
    -0.60
     Journey
    -0.60
    iel
    -0.60
     Labyrinth
    -0.57
    agog
    -0.57
    Ear
    -0.57
    zin
    -0.56
    POSITIVE LOGITS
     hampered
    1.13
     prevented
    1.11
     means
    1.09
     coupled
    1.08
     hindered
    1.08
     prevents
    1.07
     complicate
    1.06
     mean
    1.06
     hinder
    1.06
     resulted
    1.05
    Activations Density 0.508%

    No Known Activations