© 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. 11-RES-JB
    11. 6728
    Prev
    Next
    INDEX
    Explanations

    names of news organizations and their correspondents

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations or media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.76
    ãĥĹ
    -0.65
     bragging
    -0.64
    ardless
    -0.63
    comed
    -0.63
    buster
    -0.62
     1924
    -0.61
     tee
    -0.61
    lite
    -0.60
     1929
    -0.60
    POSITIVE LOGITS
     understands
    0.81
     correspondent
    0.75
    yssey
    0.71
     witness
    0.67
     Belief
    0.67
     liberties
    0.65
     Jazeera
    0.64
     Investigations
    0.62
     Arabic
    0.61
     SOU
    0.61
    Activations Density 0.099%

    No Known Activations