© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18797
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Wii console

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Wii."

    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
    onies
    -0.81
    staking
    -0.77
    ancock
    -0.76
    heid
    -0.74
    inates
    -0.73
    geant
    -0.73
    cious
    -0.71
    itute
    -0.70
    cies
    -0.70
    omaly
    -0.70
    POSITIVE LOGITS
     Fit
    0.94
    Switch
    0.90
     Wii
    0.90
    Ware
    0.90
    Pad
    0.86
    pad
    0.85
    Gear
    0.84
    Leaks
    0.83
    Way
    0.81
     Remote
    0.80
    Activations Density 0.012%

    No Known Activations