© 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. 0-RES-JB
    11. 7840
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gamer" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming culture and related personalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ray
    -0.77
     Hill
    -0.66
     Fore
    -0.65
    prints
    -0.64
     Solar
    -0.64
     counting
    -0.64
     Angola
    -0.64
     Rapids
    -0.64
     Root
    -0.63
    ien
    -0.62
    POSITIVE LOGITS
    Gamer
    2.91
    gamer
    2.29
     Milo
    2.26
     Gamer
    2.22
     GamerGate
    1.93
     Yiannopoulos
    1.90
     Gamergate
    1.85
     gamer
    1.81
    iannopoulos
    1.34
     GG
    1.32
    Activations Density 0.051%

    No Known Activations