© 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. 2-RES-JB
    11. 24196
    Prev
    Next
    INDEX
    Explanations

    positions or roles as an assistant

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of assistant positions or roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agra
    -0.75
    stakes
    -0.74
    igated
    -0.72
    igation
    -0.71
    bow
    -0.70
    aughs
    -0.68
    ongo
    -0.68
    ebook
    -0.67
    abouts
    -0.67
    fam
    -0.66
    POSITIVE LOGITS
     assistant
    1.09
     assistants
    0.90
     LIN
    0.79
     professor
    0.78
     WRITE
    0.74
     Assistant
    0.72
     coordinator
    0.70
     Siri
    0.70
     secretary
    0.70
     programmer
    0.69
    Activations Density 0.017%

    No Known Activations