© 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. 0-RES-JB
    11. 11389
    Prev
    Next
    INDEX
    Explanations

    keywords followed by a positive or negative adjective, focusing on evaluation

    oai_token-act-pair · gpt-3.5-turbo

    instances where the term "Such" and its contextual relevance are highlighted

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     folks
    -0.75
     ladies
    -0.63
     guys
    -0.62
     kids
    -0.61
     basics
    -0.58
     reset
    -0.58
     ladder
    -0.57
     everyone
    -0.57
     countdown
    -0.56
     version
    -0.56
    POSITIVE LOGITS
     Such
    3.09
    Such
    2.85
    such
    1.87
     such
    1.67
     These
    1.28
     Particularly
    1.27
     Thus
    1.20
     Those
    1.18
     Similarly
    1.17
     Moreover
    1.16
    Activations Density 0.013%

    No Known Activations