© 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. 7-RES-JB
    11. 12466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or action

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs and certain action-related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avery
    -0.70
    mong
    -0.67
    hov
    -0.66
    eway
    -0.65
    vier
    -0.65
    WER
    -0.64
    icist
    -0.64
    bold
    -0.64
    gart
    -0.63
    ateg
    -0.62
    POSITIVE LOGITS
    join
    0.66
     Chimera
    0.61
     THEM
    0.59
    strap
    0.58
     Leopard
    0.58
    ipeg
    0.57
     them
    0.56
     Scorp
    0.56
    æĸ¹
    0.56
     VIDEOS
    0.55
    Activations Density 0.273%

    No Known Activations