© 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. 13634
    Prev
    Next
    INDEX
    Explanations

    economic and policy-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social policies and their implications

    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
    shit
    -0.94
     booze
    -0.86
     shit
    -0.81
     boobs
    -0.80
     stuff
    -0.79
    stuff
    -0.77
    Yep
    -0.76
     Stuff
    -0.75
     fucking
    -0.74
    Scroll
    -0.74
    POSITIVE LOGITS
     disag
    1.04
     normative
    1.04
     policymakers
    0.98
     generalized
    0.95
     contempor
    0.95
     empir
    0.94
     contextual
    0.94
     timely
    0.93
     substantially
    0.93
     âĪ¼
    0.93
    Activations Density 1.560%

    No Known Activations