© 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. 11312
    Prev
    Next
    INDEX
    Explanations

    information related to financial implications and consequences of various events

    oai_token-act-pair · gpt-3.5-turbo

    references to economic impact and financial concerns

    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
     compliments
    -0.92
     compliment
    -0.80
     congr
    -0.75
     flattering
    -0.74
     similarity
    -0.73
     Lovely
    -0.71
     elegance
    -0.69
     Sexy
    -0.68
     mentions
    -0.68
     classy
    -0.67
    POSITIVE LOGITS
     unable
    1.35
     ineligible
    1.15
     vulnerable
    1.12
     reliant
    1.12
     unus
    1.11
     Unable
    1.08
     liable
    1.07
     unemploy
    1.05
     uninsured
    1.03
     unsustainable
    1.00
    Activations Density 0.546%

    No Known Activations