© 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. 6272
    Prev
    Next
    INDEX
    Explanations

    references to political rallies

    oai_token-act-pair · gpt-3.5-turbo

    references to political gatherings or events

    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
    etheless
    -0.77
    pei
    -0.68
    iencies
    -0.62
    ilic
    -0.60
    abilities
    -0.59
    missions
    -0.58
     Leopard
    -0.58
     Fiction
    -0.58
    Nap
    -0.58
    english
    -0.57
    POSITIVE LOGITS
     rally
    0.96
    goers
    0.92
     rallies
    0.86
    isers
    0.85
     attendees
    0.85
    halla
    0.83
    iser
    0.82
     organisers
    0.81
     Rally
    0.80
    eering
    0.79
    Activations Density 0.029%

    No Known Activations