© 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. 1740
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "rave" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "rave."

    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
    ADVERTISEMENT
    -0.69
     eval
    -0.69
     gallon
    -0.67
     color
    -0.66
     compliments
    -0.63
     nons
    -0.62
     condos
    -0.62
     Latest
    -0.61
     lin
    -0.61
     nonexistent
    -0.61
    POSITIVE LOGITS
    rave
    4.41
     Trave
    1.29
    rav
    1.19
    ravel
    1.14
    Dub
    1.07
    oeuv
    1.01
     Grave
    0.92
    riv
    0.91
     traveller
    0.88
    ipolar
    0.87
    Activations Density 0.015%

    No Known Activations