Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9642
    Prev
    Next
    INDEX
    Explanations

    references to contemporary events or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to games and gaming culture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McDonnell
    -0.74
     Prosecut
    -0.67
     Plaint
    -0.65
     Protective
    -0.61
     Mohammad
    -0.61
     Procedure
    -0.61
     plaintiff
    -0.60
     Oswald
    -0.60
     Reconstruction
    -0.58
     Prosecutor
    -0.58
    POSITIVE LOGITS
     ;)
    1.02
     :)
    1.01
    !!!!
    0.98
     nerds
    0.94
    !!!
    0.91
     lol
    0.90
     geek
    0.89
     haha
    0.89
    !!!!!
    0.88
     ðŁĺ
    0.86
    Activations Density 1.072%

    No Known Activations