© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17780
    Prev
    Next
    INDEX
    Explanations

    words related to a specific character or concept from a game or movie, possibly related to strategies or matchups

    oai_token-act-pair · gpt-3.5-turbo

    references to champions and strategies in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toys
    -0.84
     Hubbard
    -0.81
    EngineDebug
    -0.79
     TSA
    -0.75
    renheit
    -0.71
     Flavoring
    -0.71
    Reviewer
    -0.69
    OUP
    -0.69
     TED
    -0.69
    wcsstore
    -0.68
    POSITIVE LOGITS
     ADC
    0.89
     aggro
    0.84
    ande
    0.82
     minions
    0.80
     Paladin
    0.79
     defenders
    0.77
     opponent
    0.76
     ner
    0.76
     synergy
    0.76
     assassin
    0.75
    Activations Density 0.115%

    No Known Activations