© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 22601
    Prev
    Next
    INDEX
    Explanations

    mentions of deployment, especially in a military context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deploy" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    @@@@
    -0.78
    Ther
    -0.71
    iasis
    -0.69
    tha
    -0.67
    vals
    -0.67
    ����
    -0.66
    Fine
    -0.66
    $$$$
    -0.66
    neg
    -0.66
    hemat
    -0.65
    POSITIVE LOGITS
     deployments
    0.98
     Deploy
    0.93
    ploy
    0.90
     deployment
    0.88
    Deploy
    0.87
     deployed
    0.87
    ilitary
    0.81
    EStream
    0.78
     deploying
    0.78
    avorite
    0.78
    Activations Density 0.011%

    No Known Activations