© 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. 22886
    Prev
    Next
    INDEX
    Explanations

    mentions of names associated with political figures or public officials

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles of public figures

    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
     Avalon
    -0.66
     VID
    -0.65
     EVE
    -0.60
     Newtown
    -0.60
     Kodi
    -0.58
     Jericho
    -0.55
     skelet
    -0.55
     Connor
    -0.54
     subjective
    -0.54
    iHUD
    -0.54
    POSITIVE LOGITS
     confid
    0.87
    Äĩ
    0.84
    's
    0.80
    ervatives
    0.80
    zinski
    0.76
     Jinping
    0.75
     appointed
    0.74
     aide
    0.74
    tsy
    0.73
    omics
    0.73
    Activations Density 0.177%

    No Known Activations