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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    6. 5260
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific card game, focused on the mechanics and strategy of playing the game

    oai_token-act-pair · gpt-3.5-turbo

    references to specific characters, cards, or gameplay elements from a particular card game

    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
    çͰ
    -0.85
     supervised
    -0.84
     anonymously
    -0.80
     certific
    -0.75
    OPLE
    -0.72
     photographed
    -0.72
     approx
    -0.72
     fucked
    -0.70
     professionally
    -0.70
     dated
    -0.70
    POSITIVE LOGITS
    romancer
    1.19
    Blade
    1.18
    Spell
    1.16
     Cloak
    1.15
    irlwind
    1.15
     Shroud
    1.13
    mage
    1.12
     Enchant
    1.11
     Golem
    1.10
     Shield
    1.10
    Activations Density 0.165%

    No Known Activations