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. 8-RES-JB
    6. 16150
    Prev
    Next
    INDEX
    Explanations

    mentions of positions or roles within a hierarchical structure

    oai_token-act-pair · gpt-3.5-turbo

    terms related to societal issues and governance

    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
     synonymous
    -0.70
     Gaul
    -0.68
     Flip
    -0.63
    aceutical
    -0.63
    Tile
    -0.63
    orrect
    -0.61
    anmar
    -0.61
    zhen
    -0.61
    ibia
    -0.60
    arcity
    -0.59
    POSITIVE LOGITS
     microscope
    0.98
    ĵĺ
    0.78
    uary
    0.77
     radar
    0.77
     eaves
    0.76
     anesthesia
    0.74
     scanner
    0.74
    ãģĨ
    0.73
     ausp
    0.73
     guise
    0.73
    Activations Density 0.082%

    No Known Activations