Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7732
    Prev
    Next
    INDEX
    Explanations

    numbers and terms related to health points, damage, and combat skills

    oai_token-act-pair · gpt-3.5-turbo

    terms related to damage and attack mechanics in gaming

    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
     Bland
    -0.81
    sonian
    -0.78
     Homo
    -0.76
     Kinn
    -0.74
    orld
    -0.73
     Horizons
    -0.72
    ovie
    -0.72
    Redd
    -0.71
    soDeliveryDate
    -0.71
     Bellev
    -0.71
    POSITIVE LOGITS
     modifier
    1.10
     modifiers
    1.07
     potion
    1.04
     potions
    1.04
     abilities
    1.01
     dmg
    0.99
     multiplier
    0.99
     damage
    0.99
     cooldown
    0.97
     enemies
    0.97
    Activations Density 0.139%

    No Known Activations