© 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. 17448
    Prev
    Next
    INDEX
    Explanations

    organizations, research groups, projects, and institutes related to policy and research

    oai_token-act-pair · gpt-3.5-turbo

    references to research institutions and centers, particularly those involved in policy or economic studies

    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
    ãĥİ
    -0.73
     stret
    -0.70
     disapp
    -0.69
     abort
    -0.69
    touch
    -0.68
    ãĤ®
    -0.65
    inventoryQuantity
    -0.65
     Vale
    -0.63
    mast
    -0.63
     humour
    -0.62
    POSITIVE LOGITS
     Institute
    0.95
     Foundation
    0.85
     Consortium
    0.84
     LLC
    0.83
     LLP
    0.81
    orer
    0.79
    ortium
    0.76
     Investigative
    0.75
    tery
    0.75
     Initiative
    0.74
    Activations Density 0.115%

    No Known Activations