© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1-RES-JB
    11. 20483
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the brand "Sky" and its products or services

    oai_token-act-pair · gpt-3.5-turbo

    references to the brand or entity "Sky"

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    女
    -0.79
    aunder
    -0.70
    000000
    -0.69
    lication
    -0.68
    0000000
    -0.67
    atives
    -0.65
    utics
    -0.64
    aphael
    -0.64
    Ô
    -0.64
     Lovecraft
    -0.60
    POSITIVE LOGITS
    Sky
    1.02
     Sky
    0.97
    bone
    0.91
    lake
    0.90
    fax
    0.86
    hawk
    0.85
    link
    0.82
    eus
    0.80
    Eye
    0.78
    landers
    0.78
    Activations Density 0.005%

    No Known Activations