© 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
    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. 8724
    Prev
    Next
    INDEX
    Explanations

    game-related terms or abilities such as "paralyze," "damage," and "knockback."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to game mechanics, particularly those involving abilities and damage effects

    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
    soDeliveryDate
    -1.08
     handwriting
    -0.82
     autobi
    -0.78
     Adidas
    -0.74
    sonian
    -0.74
    ploma
    -0.73
     reinvent
    -0.73
    çīĪ
    -0.72
     PowerPoint
    -0.71
     certificates
    -0.70
    POSITIVE LOGITS
     melee
    1.48
     enemy
    1.40
     enemies
    1.40
    enemy
    1.30
     foes
    1.28
     projectiles
    1.28
     aggro
    1.23
     mobs
    1.22
     respawn
    1.21
     spawns
    1.18
    Activations Density 0.494%

    No Known Activations