© 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. 6479
    Prev
    Next
    INDEX
    Explanations

    mention of various forms of media, such as traditional media outlets, the internet, or particular organizations like the BBC or the military

    oai_token-act-pair · gpt-3.5-turbo

    terms related to media and technology

    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
    hots
    -0.78
    lear
    -0.68
    ioned
    -0.66
    conserv
    -0.64
    viol
    -0.64
    speak
    -0.62
    edIn
    -0.61
    tions
    -0.61
    laus
    -0.61
    hot
    -0.61
    POSITIVE LOGITS
     itself
    1.02
    osphere
    1.00
     ecosystem
    0.97
     microbiome
    0.97
     economy
    0.94
     sphere
    0.91
     continuum
    0.88
     sector
    0.87
     workforce
    0.87
     hierarchy
    0.86
    Activations Density 0.381%

    No Known Activations