© 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. 22972
    Prev
    Next
    INDEX
    Explanations

    references to the publication "The Huffington Post"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of news outlets, particularly "The Huffington Post" and "The Daily Beast."

    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
    ĪĴ
    -0.85
    gone
    -0.78
    Ö¼
    -0.76
     tide
    -0.75
    NetMessage
    -0.70
    ardless
    -0.69
    oku
    -0.66
    capacity
    -0.65
    inant
    -0.65
     psi
    -0.63
    POSITIVE LOGITS
     Archive
    0.89
     Editorial
    0.88
     Digest
    0.85
     Editors
    0.84
     Magazine
    0.82
     Correspond
    0.81
     Gazette
    0.80
    Leaks
    0.80
    lished
    0.79
     Publishing
    0.79
    Activations Density 0.056%

    No Known Activations