© 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. 22150
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to the name "Shane"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Shane" prominently mentioned in various contexts

    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
    é¾įå¥ij士
    -1.19
    女
    -0.93
    rontal
    -0.91
    ¥µ
    -0.85
    insula
    -0.80
    ollower
    -0.77
    anwhile
    -0.75
    astics
    -0.74
    ental
    -0.74
    yrinth
    -0.74
    POSITIVE LOGITS
     Shane
    1.06
     McMahon
    0.91
     Greene
    0.83
     Leone
    0.78
     Dixon
    0.75
     Bauer
    0.74
    vel
    0.72
     Moran
    0.72
     Dempsey
    0.72
     Wade
    0.70
    Activations Density 0.010%

    No Known Activations