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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6271
    Prev
    Next
    INDEX
    Explanations

    information related to weaponry, damage, power-ups, and game mechanics

    oai_token-act-pair · gpt-3.5-turbo

    attributes and effects related to weapons or abilities 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 @ 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
    Reviewer
    -0.98
    çͰ
    -0.75
    liga
    -0.73
     notebooks
    -0.72
    osures
    -0.72
    Topics
    -0.69
    prises
    -0.69
    eday
    -0.69
     aisle
    -0.69
     Homo
    -0.68
    POSITIVE LOGITS
     cooldown
    1.35
     Cooldown
    1.34
     Damage
    1.24
     damage
    1.21
    Damage
    1.16
     heals
    1.16
     Healing
    1.14
    damage
    1.14
     healing
    1.12
    Cooldown
    1.11
    Activations Density 0.179%

    No Known Activations