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. 18696
    Prev
    Next
    INDEX
    Explanations

    mentions of services related to the military, such as servicemen, service demands, and service members

    oai_token-act-pair · gpt-3.5-turbo

    references to service-related roles and traditional processes

    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
    urrent
    -0.77
    mpeg
    -0.68
     Kurd
    -0.66
     Gab
    -0.64
    isions
    -0.63
     Salman
    -0.62
    izon
    -0.62
    oker
    -0.60
     Karachi
    -0.60
    asper
    -0.59
    POSITIVE LOGITS
    eman
    1.04
    emate
    1.00
    ework
    0.98
    eways
    0.97
    ename
    0.96
    ewater
    0.91
    eworks
    0.90
    estyles
    0.89
    emen
    0.88
    estyle
    0.84
    Activations Density 0.060%

    No Known Activations