© 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. 352
    Prev
    Next
    INDEX
    Explanations

    websites and technology-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to social media platforms and genres of storytelling

    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
     counterpart
    -0.47
     hindsight
    -0.42
     proceed
    -0.41
     presumptive
    -0.41
     Democr
    -0.39
    imilar
    -0.39
    lished
    -0.39
     coincides
    -0.38
    ensional
    -0.38
    uchin
    -0.38
    POSITIVE LOGITS
     etc
    1.09
    etc
    0.88
    âĢ¦)
    0.62
    ))))
    0.55
     respectively
    0.53
     âĢ¦
    0.52
    âĢ¦.
    0.52
     };
    0.50
    ...)
    0.50
    )).
    0.48
    Activations Density 0.830%

    No Known Activations