© 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. 2-RES-JB
    11. 17249
    Prev
    Next
    INDEX
    Explanations

    frequent mentions of the name "Miles."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chnology
    -0.82
    ulhu
    -0.72
    ibaba
    -0.67
    perors
    -0.66
    ebin
    -0.66
    anooga
    -0.66
    yrinth
    -0.66
    cheat
    -0.66
     redistributed
    -0.65
    etheus
    -0.65
    POSITIVE LOGITS
     Miles
    1.23
     Cheong
    1.11
     Higgins
    0.95
     Morales
    0.93
     Leone
    0.92
     Davis
    0.90
     Gardner
    0.89
     Faul
    0.86
     Armstrong
    0.85
     Skinner
    0.82
    Activations Density 0.009%

    No Known Activations