© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6904
    Prev
    Next
    INDEX
    Explanations

    phrases related to international conflicts or disputes

    oai_token-act-pair · gpt-3.5-turbo

    recurring phrases involving the word "and" in various contexts

    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
    Discuss
    -0.75
    quest
    -0.74
    wow
    -0.72
    bard
    -0.70
    ftime
    -0.70
    notations
    -0.69
    kar
    -0.67
    Names
    -0.67
    ccording
    -0.67
    ï¸
    -0.66
    POSITIVE LOGITS
     vanquished
    0.75
     its
    0.67
     Frem
    0.66
     Victory
    0.64
     Olympia
    0.64
     Hamilton
    0.64
     Gam
    0.63
     Chinatown
    0.63
     Great
    0.62
     adversity
    0.62
    Activations Density 0.101%

    No Known Activations