© 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. 9-RES-JB
    11. 3064
    Prev
    Next
    INDEX
    Explanations

    mentions of economic and social policy discussions related to taxation and welfare

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating socioeconomic disparities and discussions about wealth distribution

    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
    manship
    -0.82
    boards
    -0.68
    wcsstore
    -0.66
    pin
    -0.65
    ship
    -0.65
    tackle
    -0.64
    stan
    -0.64
     FILE
    -0.64
    fulness
    -0.61
    iHUD
    -0.60
    POSITIVE LOGITS
     poorest
    1.38
     wealthiest
    1.36
     elderly
    1.34
     masses
    1.22
     unemployed
    1.19
     populace
    1.18
     richest
    1.14
     wealthy
    1.13
     sexes
    1.13
     needy
    1.13
    Activations Density 0.332%

    No Known Activations