© 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. 9-RES-JB
    11. 10197
    Prev
    Next
    INDEX
    Explanations

    the name "Philip."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Philip."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lly
    -0.80
    cession
    -0.75
    eer
    -0.72
    bnb
    -0.72
    ãĤ§
    -0.71
    DERR
    -0.70
    cial
    -0.69
    eers
    -0.67
    system
    -0.65
    yrinth
    -0.64
    POSITIVE LOGITS
     Morris
    0.90
     Randolph
    0.85
     Seymour
    0.76
    son
    0.76
     Pull
    0.71
     Islands
    0.71
     Rivers
    0.69
     Wad
    0.68
     Maced
    0.68
     Hammond
    0.66
    Activations Density 0.032%

    No Known Activations