© 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. 4-RES-JB
    11. 7102
    Prev
    Next
    INDEX
    Explanations

    references to different Nintendo gaming consoles

    oai_token-act-pair · gpt-3.5-turbo

    references to Nintendo gaming consoles and their versions

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

    No Comments

    Negative Logits
     crem
    -0.67
    æ³
    -0.67
     scient
    -0.63
     sanct
    -0.62
     rh
    -0.62
     PLAN
    -0.61
     improv
    -0.61
     hed
    -0.59
     resc
    -0.58
     sheltered
    -0.57
    POSITIVE LOGITS
    Xbox
    1.06
     Wii
    0.96
     consoles
    0.93
    Console
    0.91
     PlayStation
    0.87
     Playstation
    0.83
    Nintendo
    0.81
    console
    0.80
     emulator
    0.80
     SLI
    0.80
    Activations Density 0.055%

    No Known Activations