© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3144
    Prev
    Next
    INDEX
    Explanations

    terms related to attack attributes in a gaming context

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kinn
    -0.79
    ovie
    -0.78
     Bland
    -0.76
    orld
    -0.72
    dated
    -0.72
     Bridgewater
    -0.71
    isle
    -0.70
    Redd
    -0.69
    cession
    -0.69
    ļéĨĴ
    -0.69
    POSITIVE LOGITS
     modifier
    1.04
     cooldown
    1.03
     modifiers
    0.97
     Cooldown
    0.96
     abilities
    0.93
     potions
    0.90
     piercing
    0.90
     runes
    0.87
    Damage
    0.87
     combos
    0.84
    Activations Density 0.145%

    No Known Activations