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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 1034
    Prev
    Next
    INDEX
    Explanations

    references to the publication "Business Insider."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Business Insider" and associated entities or events

    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
     tide
    -0.64
    alogue
    -0.64
     cath
    -0.62
     sovere
    -0.62
     COURT
    -0.59
     obser
    -0.59
    wid
    -0.57
    itimate
    -0.57
    anical
    -0.56
     welf
    -0.56
    POSITIVE LOGITS
    ®
    0.87
     Magazine
    0.86
     magazine
    0.85
    ®,
    0.85
     Presents
    0.83
     ®
    0.80
    uggets
    0.78
     Digest
    0.78
     Ltd
    0.77
     LLP
    0.74
    Activations Density 0.120%

    No Known Activations