© 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 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. 3-RES-JB
    11. 3696
    Prev
    Next
    INDEX
    Explanations

    words related to a specific video game franchise

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the "Gear" series of products, particularly related to gaming

    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
     denomin
    -0.88
    venue
    -0.82
    iversal
    -0.79
     CTR
    -0.75
    minist
    -0.73
    umbn
    -0.71
    udeb
    -0.69
    emet
    -0.68
    enance
    -0.67
    unct
    -0.66
    POSITIVE LOGITS
     Gear
    0.99
    Gear
    0.97
    bag
    0.80
    VR
    0.80
    box
    0.80
    Feed
    0.79
     GEAR
    0.79
     gadgets
    0.78
     VR
    0.77
    Bone
    0.73
    Activations Density 0.009%

    No Known Activations