© 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. 1-RES-JB
    11. 18791
    Prev
    Next
    INDEX
    Explanations

    references to the video game "World of Warcraft."

    oai_token-act-pair · gpt-3.5-turbo

    references to the game World of Warcraft and its related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elin
    -0.76
    oning
    -0.70
    iden
    -0.70
     puzzle
    -0.70
    othy
    -0.68
    UNCH
    -0.67
     slit
    -0.65
    otherapy
    -0.64
    Assembly
    -0.64
    odynamic
    -0.64
    POSITIVE LOGITS
    %%%%
    0.98
    umes
    0.78
    Footnote
    0.72
    eus
    0.71
    urious
    0.71
    uve
    0.69
    entials
    0.69
    lihood
    0.68
    phrine
    0.67
    ð
    0.66
    Activations Density 0.029%

    No Known Activations