© 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. 8-RES-JB
    11. 9475
    Prev
    Next
    INDEX
    Explanations

    phrases related to the game "Whack-a-Mole."

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to games or competition

    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
    mand
    -0.74
    ItemImage
    -0.70
    RIC
    -0.69
    mere
    -0.66
    Introduced
    -0.64
    rome
    -0.63
     Lank
    -0.61
    Price
    -0.60
    izabeth
    -0.59
    FF
    -0.58
    POSITIVE LOGITS
    shit
    0.72
    Cola
    0.66
     Juice
    0.65
     bucket
    0.64
     Hits
    0.63
    ĵĺ
    0.63
     asses
    0.63
    buck
    0.63
    crazy
    0.61
     luck
    0.61
    Activations Density 0.192%

    No Known Activations