© 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. 2275
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, such as political figures

    oai_token-act-pair · gpt-3.5-turbo

    names and titles of prominent individuals, particularly in political contexts

    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
    ĸļ
    -0.73
     BMC
    -0.69
    pta
    -0.68
     gui
    -0.63
     Crim
    -0.60
     Citiz
    -0.60
    odder
    -0.60
     [|
    -0.59
    ipeg
    -0.58
    ancial
    -0.57
    POSITIVE LOGITS
     Corker
    0.92
    fman
    0.78
    socket
    0.66
     Tillerson
    0.65
     Cosponsors
    0.65
    Lago
    0.65
     boycot
    0.64
     uranium
    0.64
     Flake
    0.63
     Schumer
    0.63
    Activations Density 0.837%

    No Known Activations