© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 15143
    Prev
    Next
    INDEX
    Explanations

    phrases related to gaming and combat

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to game mechanics and damage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contrace
    -0.93
     Draper
    -0.85
    eteenth
    -0.82
     blogger
    -0.79
     whistleblowers
    -0.79
     enthusi
    -0.79
     Oprah
    -0.78
     contraceptives
    -0.78
     UNCLASSIFIED
    -0.78
     handwriting
    -0.77
    POSITIVE LOGITS
     melee
    1.23
     respawn
    1.17
     Melee
    1.16
     NPCs
    1.12
     PvP
    1.09
    Gameplay
    1.08
     Enchant
    1.08
     cooldown
    1.06
     Aether
    1.05
     Abilities
    1.05
    Activations Density 1.119%

    No Known Activations