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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 6344
    Prev
    Next
    INDEX
    Explanations

    mentions of assistant positions in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the term "assistant" in various contexts, particularly in professional or official titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ktop
    -0.75
    abiding
    -0.71
    stakes
    -0.71
    ERO
    -0.71
    naire
    -0.70
    ebook
    -0.66
    ongo
    -0.66
    rust
    -0.65
    Winged
    -0.65
    naires
    -0.65
    POSITIVE LOGITS
     professor
    1.04
     secretary
    0.84
     dean
    0.83
     assistant
    0.82
     director
    0.81
     superintendent
    0.81
     pastor
    0.80
     secretaries
    0.78
     principal
    0.75
    getic
    0.74
    Activations Density 0.025%

    No Known Activations