© 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. 8-RES-JB
    11. 17769
    Prev
    Next
    INDEX
    Explanations

    words related to journalism, news, and providing information in an open and accessible manner

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transparency and support in journalism

    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
    axter
    -0.68
    lihood
    -0.64
    ortium
    -0.62
     hindsight
    -0.62
    uthor
    -0.61
    alog
    -0.60
    Reviewed
    -0.60
     Warrant
    -0.59
    ometric
    -0.58
    hift
    -0.58
    POSITIVE LOGITS
    iphate
    0.82
    iframe
    0.69
     Judiciary
    0.66
     Mechdragon
    0.63
    essors
    0.61
    æ©
    0.61
    ods
    0.60
    inia
    0.60
    Ni
    0.60
    ennis
    0.60
    Activations Density 0.058%

    No Known Activations