© 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. 4-RES-JB
    11. 6319
    Prev
    Next
    INDEX
    Explanations

    terms related to different aspects or components of a subject

    oai_token-act-pair · gpt-3.5-turbo

    terms that describe various aspects or components of subjects discussed

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

    No Comments

    Negative Logits
    /
    -0.74
    weather
    -0.74
    zan
    -0.72
    ctic
    -0.72
    cellaneous
    -0.68
    Whit
    -0.68
    legal
    -0.68
    active
    -0.67
    wana
    -0.67
    è¦ļéĨĴ
    -0.66
    POSITIVE LOGITS
     contestant
    0.70
     outweigh
    0.69
     entails
    0.67
     Mafia
    0.63
     Starcraft
    0.60
     portion
    0.60
     Bulg
    0.57
     StarCraft
    0.57
     exceeds
    0.57
     contestants
    0.57
    Activations Density 0.417%

    No Known Activations