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. 10-RES-JB
    6. 4212
    Prev
    Next
    INDEX
    Explanations

    words related to Apple products and services

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     optics
    -0.63
     issuing
    -0.62
     alternate
    -0.61
     Everett
    -0.61
    rero
    -0.60
     orally
    -0.59
     Illum
    -0.59
     overturn
    -0.58
     unpublished
    -0.58
     annex
    -0.58
    POSITIVE LOGITS
    wi
    1.13
    GPU
    1.11
    Heart
    1.09
    ota
    1.06
    amins
    1.02
    ibo
    1.01
    HUD
    0.99
    pec
    0.96
    Movie
    0.95
    Shares
    0.95
    Activations Density 0.014%

    No Known Activations