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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 16295
    Prev
    Next
    INDEX
    Explanations

    words related to deploying or implementation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "deployed" and related terms indicating the implementation or placement of resources or personnel

    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
    opia
    -0.64
    answer
    -0.63
    terms
    -0.62
    ibliography
    -0.62
     Draw
    -0.60
    show
    -0.59
     Hobbit
    -0.59
    record
    -0.58
     repentance
    -0.58
     Journals
    -0.58
    POSITIVE LOGITS
     deployed
    3.12
     stationed
    2.05
     dispatched
    1.84
     employed
    1.79
     tasked
    1.78
     mobilized
    1.71
     fielded
    1.62
     activated
    1.59
     utilized
    1.48
     positioned
    1.45
    Activations Density 0.026%

    No Known Activations