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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15725
    Prev
    Next
    INDEX
    Explanations

    words related to military personnel and operations

    oai_token-act-pair · gpt-3.5-turbo

    references to military personnel and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Invention
    -0.76
    ãĤ¦ãĤ¹
    -0.76
    theless
    -0.71
     Studio
    -0.71
     Rowling
    -0.71
    âĸ¬
    -0.70
    DERR
    -0.69
     straw
    -0.68
     Thumbnails
    -0.66
     bulb
    -0.64
    POSITIVE LOGITS
     stationed
    1.68
     garrison
    1.22
     patrolling
    1.21
     deployed
    1.19
     fatig
    1.15
     guarding
    1.10
     marching
    1.09
     colonel
    1.07
     barracks
    1.04
     loyal
    1.04
    Activations Density 0.101%

    No Known Activations