© 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 EvalsExportsinterp-engineNEWAPI 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. 1134
    Prev
    Next
    INDEX
    Explanations

    references to gaming consoles, particularly the PlayStation 4 and Xbox One

    oai_token-act-pair · gpt-3.5-turbo

    references to specific 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 @ 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
    atories
    -0.85
    atory
    -0.76
    eering
    -0.73
    staff
    -0.72
    reek
    -0.71
    tnc
    -0.70
    aith
    -0.69
     Faul
    -0.67
    arial
    -0.66
    displayText
    -0.65
    POSITIVE LOGITS
     Slim
    0.93
    Xbox
    0.85
     Classics
    0.85
    ®,
    0.83
    BSD
    0.81
     Exclusive
    0.79
    âĦ¢
    0.79
     Adapter
    0.77
    Games
    0.77
     Controller
    0.77
    Activations Density 0.036%

    No Known Activations