© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 24357
    Prev
    Next
    INDEX
    Explanations

    proper names of people (Tony) and possibly celebrity names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Tony."

    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
    INESS
    -0.92
    cipline
    -0.74
    ebook
    -0.72
    ãģ¦
    -0.72
    doors
    -0.72
    baugh
    -0.71
    BOOK
    -0.70
    IFT
    -0.69
    pmwiki
    -0.68
    Magikarp
    -0.68
    POSITIVE LOGITS
     Abbott
    0.94
     Blair
    0.90
     Romo
    0.86
     Tony
    0.85
     Sop
    0.85
    neau
    0.81
     Stark
    0.81
     Hawk
    0.79
    anto
    0.76
    onga
    0.76
    Activations Density 0.009%

    No Known Activations