© 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. 16883
    Prev
    Next
    INDEX
    Explanations

    discussion about the sustainability and quality of publications

    oai_token-act-pair · gpt-3.5-turbo

    references to high-quality publications and their sustainability challenges in the media industry

    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
    zac
    -0.84
    Footnote
    -0.73
    amen
    -0.72
    witz
    -0.72
     Predators
    -0.67
    aughs
    -0.67
    bara
    -0.66
    Registered
    -0.65
    ovember
    -0.65
    pport
    -0.65
    POSITIVE LOGITS
    é¾įå
    0.76
    èĪ
    0.74
    entimes
    0.73
    æĺ
    0.72
     offerings
    0.70
    iframe
    0.70
    Independent
    0.69
    VK
    0.67
     domain
    0.63
    osion
    0.62
    Activations Density 0.032%

    No Known Activations