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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18542
    Prev
    Next
    INDEX
    Explanations

    terms related to military strategies and units

    oai_token-act-pair · gpt-3.5-turbo

    terms related to units and military strategy 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 @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displayText
    -0.87
    çīĪ
    -0.85
     prosecut
    -0.81
     Weiner
    -0.70
    à¦
    -0.70
    ļéĨĴ
    -0.70
    taboola
    -0.69
    RH
    -0.69
     videot
    -0.68
    ESSION
    -0.68
    POSITIVE LOGITS
     turrets
    1.02
     mech
    1.01
     armor
    0.94
     armour
    0.90
     NPCs
    0.89
     faction
    0.88
    combat
    0.88
     respawn
    0.88
     spawns
    0.87
     marines
    0.86
    Activations Density 0.278%

    No Known Activations