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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 576
    Prev
    Next
    INDEX
    Explanations

    names or titles related to White House officials

    oai_token-act-pair · gpt-3.5-turbo

    references to figures in the White House press and communication roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     relegation
    -0.73
     Pione
    -0.69
     emanc
    -0.68
     Worcester
    -0.67
     extinct
    -0.65
     Farmers
    -0.64
     Providence
    -0.64
     steril
    -0.62
    Rated
    -0.62
     medicinal
    -0.61
    POSITIVE LOGITS
     Sean
    0.85
    afort
    0.82
     Dmitry
    0.79
     aide
    0.77
     Ari
    0.74
     Katie
    0.74
     Adviser
    0.72
    gey
    0.71
     adviser
    0.71
    chair
    0.69
    Activations Density 0.103%

    No Known Activations