© 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. 23535
    Prev
    Next
    INDEX
    Explanations

    references to a specific news organization, specifically "Guardian."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "The Guardian" media outlet

    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
    perm
    -0.87
    cles
    -0.84
    itionally
    -0.84
    lease
    -0.82
    anners
    -0.76
    inant
    -0.75
    ramid
    -0.74
    jri
    -0.74
    merce
    -0.74
    NetMessage
    -0.72
    POSITIVE LOGITS
     Angels
    1.00
     Editorial
    0.92
     Angel
    0.85
     Observer
    0.82
     Newsp
    0.79
     Newspaper
    0.79
    Leaks
    0.78
     columnist
    0.78
     Agency
    0.77
     Correspond
    0.77
    Activations Density 0.022%

    No Known Activations