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. 21410
    Prev
    Next
    INDEX
    Explanations

    phrases related to escalation or escalating situations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to escalating conflicts or tensions

    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
    avering
    -0.88
    itte
    -0.85
     Tycoon
    -0.74
    yard
    -0.74
    ãĥĩãĤ£
    -0.74
    maker
    -0.72
    ieu
    -0.72
    busters
    -0.72
    spot
    -0.72
     Maker
    -0.72
    POSITIVE LOGITS
     escalation
    1.21
     escal
    1.18
     escalate
    1.10
    escal
    0.99
     escalating
    0.94
    wcs
    0.90
    xual
    0.89
    uates
    0.83
     tensions
    0.81
    uations
    0.80
    Activations Density 0.017%

    No Known Activations