© 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. 13957
    Prev
    Next
    INDEX
    Explanations

    terms related to public policy and socio-economic issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, welfare, trade, and economic factors

    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
    DragonMagazine
    -0.73
    ortium
    -0.73
    htaking
    -0.69
     Canaver
    -0.69
    pherd
    -0.68
    hari
    -0.67
    igl
    -0.67
    partisan
    -0.66
     Mermaid
    -0.66
    interstitial
    -0.64
    POSITIVE LOGITS
     outcomes
    1.18
     activities
    1.02
     behaviors
    1.00
     stimuli
    0.92
     activity
    0.90
     behaviours
    0.90
     interventions
    0.90
     decisions
    0.89
     products
    0.89
     situations
    0.88
    Activations Density 0.427%

    No Known Activations