© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 4131
    Prev
    Next
    INDEX
    Explanations

    mentions of titles or terms related to recognition or honor, such as "Priest" or "Prize"

    oai_token-act-pair · gpt-3.5-turbo

    references to awards or prizes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -1.21
    lihood
    -0.76
    icago
    -0.75
    ding
    -0.72
    schild
    -0.72
    ded
    -0.71
     Leilan
    -0.67
     dred
    -0.64
     HELL
    -0.63
     Wink
    -0.62
    POSITIVE LOGITS
    ests
    1.11
    ety
    1.08
    etary
    1.07
    zes
    1.05
    eties
    1.04
    esses
    0.97
    heed
    0.87
    archs
    0.87
    ë
    0.85
    eur
    0.83
    Activations Density 0.012%

    No Known Activations