© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1476
    Prev
    Next
    INDEX
    Explanations

    items that are items listed or mentioned, possibly in a catalog or a review

    oai_token-act-pair · gpt-3.5-turbo

    elements of sentence structure or punctuation

    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
    abwe
    -0.82
     annex
    -0.80
     inflation
    -0.79
     uranium
    -0.75
     uninsured
    -0.74
     allied
    -0.74
    ĪĴ
    -0.73
     economics
    -0.72
     consolidate
    -0.72
    cius
    -0.70
    POSITIVE LOGITS
    PHOTOS
    1.18
    SEE
    1.18
    Fans
    1.09
    However
    1.06
    Anonymous
    1.05
    Cele
    1.04
    Advertisement
    1.01
    Screenshot
    1.01
    SPONSORED
    1.00
    YouTube
    1.00
    Activations Density 0.638%

    No Known Activations