© 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. 8-RES-JB
    11. 7913
    Prev
    Next
    INDEX
    Explanations

    descriptions of parts of things or larger quantities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to injuries and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presided
    -0.63
     recess
    -0.61
    ente
    -0.60
    oris
    -0.58
     industrialized
    -0.56
    meet
    -0.55
     adaptation
    -0.54
     supervision
    -0.53
    opt
    -0.53
     appoint
    -0.53
    POSITIVE LOGITS
    abytes
    0.81
     stains
    0.73
     fragments
    0.73
    artifacts
    0.71
    âĵĺ
    0.70
     scratches
    0.68
     souven
    0.68
    umbnails
    0.67
    estones
    0.67
     artifacts
    0.66
    Activations Density 1.028%

    No Known Activations