© 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. 22478
    Prev
    Next
    INDEX
    Explanations

    newsletters or articles that are delivered to an inbox

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the delivery of news and information

    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
    perty
    -0.74
    wikipedia
    -0.72
    é¾įå
    -0.64
    conn
    -0.62
     Kirin
    -0.61
    hift
    -0.61
    mare
    -0.60
     conce
    -0.59
     Geh
    -0.59
    aji
    -0.58
    POSITIVE LOGITS
    imentary
    0.87
     weekday
    0.79
     delivered
    0.77
     Subscribe
    0.76
    Interstitial
    0.70
     subscribe
    0.70
    iverse
    0.69
    ocument
    0.69
     electronically
    0.67
    desktop
    0.67
    Activations Density 0.030%

    No Known Activations