© 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. 17479
    Prev
    Next
    INDEX
    Explanations

    legislation-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to specific legislative bills and acts

    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
     Passion
    -0.68
     wandering
    -0.67
     Prophet
    -0.66
     Cry
    -0.65
     destiny
    -0.63
     Expedition
    -0.63
     Syndrome
    -0.62
     Royale
    -0.61
     Yellow
    -0.61
     Fever
    -0.59
    POSITIVE LOGITS
     proposes
    1.50
     mandates
    1.28
     eliminates
    1.28
     prohibits
    1.26
     imposes
    1.19
     aims
    1.18
     seeks
    1.14
    osponsors
    1.13
     specifies
    1.12
    ospons
    1.11
    Activations Density 0.262%

    No Known Activations