© 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. 10577
    Prev
    Next
    INDEX
    Explanations

    website URLs and programming-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific URLs or links associated with technology

    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
    ô
    -0.77
    ÃĥÃĤÃĥÃĤ
    -0.73
    Þ
    -0.72
     Cham
    -0.71
    ß
    -0.69
     Boo
    -0.68
     earthqu
    -0.67
     Eighth
    -0.67
     Phi
    -0.67
     HMS
    -0.67
    POSITIVE LOGITS
    cdn
    1.50
    forums
    1.36
    wiki
    1.28
    online
    1.25
    planet
    1.19
    pedia
    1.16
    archive
    1.16
    archives
    1.16
    upload
    1.15
    nexus
    1.10
    Activations Density 0.067%

    No Known Activations