© 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. 6980
    Prev
    Next
    INDEX
    Explanations

    references to the entity "Nintendo"

    oai_token-act-pair · gpt-3.5-turbo

    references to Nintendo and its products

    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
    aneers
    -0.73
     McKenna
    -0.72
    chell
    -0.70
    onies
    -0.66
    oning
    -0.66
    lain
    -0.64
    mary
    -0.63
    haar
    -0.63
    annis
    -0.63
     LAPD
    -0.63
    POSITIVE LOGITS
     Wii
    0.95
    Switch
    0.93
    intendo
    0.83
     Hots
    0.81
     Characters
    0.78
     Logo
    0.75
    Nintendo
    0.75
     Switch
    0.74
    itsu
    0.74
     Coil
    0.74
    Activations Density 0.020%

    No Known Activations