© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 24160
    Prev
    Next
    INDEX
    Explanations

    words related to the video game "Counter-Strike"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Strike" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ission
    -0.95
    itability
    -0.84
    ocide
    -0.83
    aimon
    -0.82
    ophe
    -0.80
    umbn
    -0.80
    umption
    -0.80
    ocent
    -0.79
     tremend
    -0.79
    ophers
    -0.78
    POSITIVE LOGITS
    breakers
    0.92
    Strike
    0.90
    force
    0.87
     Fighter
    0.82
     Force
    0.79
     Strike
    0.79
    breaker
    0.77
     Dynamics
    0.75
    deen
    0.74
     Witches
    0.73
    Activations Density 0.013%

    No Known Activations