© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3283
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific person or political figure named "Pr"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions or references to a specific individual or entity, denoted by "Pr"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.74
     EntityItem
    -0.73
    HUD
    -0.69
    INESS
    -0.67
    rities
    -0.64
    RAFT
    -0.63
     SOLD
    -0.62
    STER
    -0.62
    ãĥ¼ãĥ«
    -0.62
     spirited
    -0.61
    POSITIVE LOGITS
    atche
    1.16
    udence
    1.13
    imes
    1.07
    ima
    1.03
    acking
    0.94
    acks
    0.94
    acing
    0.94
    ussia
    0.93
    ud
    0.92
    ag
    0.91
    Activations Density 0.007%

    No Known Activations