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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 18136
    Prev
    Next
    INDEX
    Explanations

    words related to political aides

    oai_token-act-pair · gpt-3.5-turbo

    references to aides or assistants in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aval
    -0.71
    itiveness
    -0.70
    Population
    -0.69
    PATH
    -0.69
    istic
    -0.68
    MQ
    -0.67
    EVA
    -0.66
     Rio
    -0.65
     Sabha
    -0.62
    DEV
    -0.62
    POSITIVE LOGITS
     Huma
    0.98
     tasked
    0.85
     aide
    0.84
    maid
    0.79
     aides
    0.73
    zu
    0.71
     counsel
    0.71
    agents
    0.71
    ster
    0.70
    wife
    0.69
    Activations Density 0.031%

    No Known Activations