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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 11087
    Prev
    Next
    INDEX
    Explanations

    phrases related to deployment of technology or military resources

    oai_token-act-pair · gpt-3.5-turbo

    mentions of deployment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tate
    -0.82
     Frie
    -0.79
     Whitney
    -0.73
     Floyd
    -0.71
     Giovanni
    -0.70
    ree
    -0.70
     Rahman
    -0.69
    rat
    -0.68
     Rabb
    -0.67
     Eater
    -0.67
    POSITIVE LOGITS
     deployment
    3.32
     deploy
    3.21
     deployments
    2.99
     deployed
    2.73
     deploying
    2.70
     Deploy
    2.66
    Deploy
    2.53
    ploy
    2.19
     rollout
    1.57
     rede
    1.51
    Activations Density 0.021%

    No Known Activations