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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 16899
    Prev
    Next
    INDEX
    Explanations

    terms related to different modes in video games

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating different modes of an interactive experience, particularly in a gaming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retri
    -0.73
    folk
    -0.60
    jri
    -0.59
    ,,,,
    -0.58
     bicycl
    -0.58
    lag
    -0.57
    sembly
    -0.57
     insepar
    -0.56
     mete
    -0.56
     recl
    -0.55
    POSITIVE LOGITS
     Thumbnails
    1.09
     Mode
    0.79
    advertisement
    0.75
     IMAGES
    0.75
     Content
    0.72
     Theatre
    0.72
     WATCHED
    0.70
     Below
    0.67
    VERTISEMENT
    0.61
    åĭ
    0.61
    Activations Density 0.014%

    No Known Activations