© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 13820
    Prev
    Next
    INDEX
    Explanations

    words related to action or process that involves the handling, management, or alteration of various factors or entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of "ation" or processes and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    JO
    -0.71
     Bridges
    -0.61
     levers
    -0.58
     neigh
    -0.58
    åŃIJ
    -0.58
     challeng
    -0.55
     Mith
    -0.54
     metic
    -0.53
     HIGH
    -0.53
     statically
    -0.53
    POSITIVE LOGITS
    ation
    4.11
    ations
    2.85
    ATION
    2.26
    ated
    2.21
    ating
    2.02
    ATIONS
    1.92
    ational
    1.83
    ators
    1.81
    ative
    1.76
    ator
    1.73
    Activations Density 0.015%

    No Known Activations