© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11478
    Prev
    Next
    INDEX
    Explanations

    texts discussing roles or actions of individuals in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating existence, state, or necessity of actions and 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
     Seym
    -0.69
     Vaugh
    -0.68
    Honest
    -0.68
     Niet
    -0.63
     COUR
    -0.62
     advoc
    -0.61
    Aud
    -0.60
    æĪ
    -0.59
    Ton
    -0.58
    esides
    -0.58
    POSITIVE LOGITS
    Ĥª
    0.70
     decreased
    0.58
    aves
    0.58
     guiActiveUnfocused
    0.57
     prolifer
    0.57
     largeDownload
    0.56
    hee
    0.55
    cing
    0.55
    icing
    0.53
    metics
    0.53
    Activations Density 0.431%

    No Known Activations