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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 19036
    Prev
    Next
    INDEX
    Explanations

    phrases related to deterrence, especially in the context of military power and international relations

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to deterrents and deterrence

    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
    ucket
    -0.79
    apor
    -0.78
    oln
    -0.77
     Horizon
    -0.75
    ugen
    -0.74
     Created
    -0.71
    atche
    -0.70
     rooft
    -0.70
     Printed
    -0.69
    hai
    -0.68
    POSITIVE LOGITS
     deterrent
    1.28
    ministic
    1.13
     deterrence
    1.01
    minist
    0.89
     reinforcement
    0.85
    etheless
    0.81
     enthusi
    0.78
     destro
    0.76
     juven
    0.74
     tyr
    0.74
    Activations Density 0.022%

    No Known Activations