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. 8-RES-JB
    6. 12703
    Prev
    Next
    INDEX
    Explanations

    keywords related to movie settings and modes

    oai_token-act-pair · gpt-3.5-turbo

    references to game modes and exit strategies in gameplay contexts

    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
     retri
    -0.79
     passer
    -0.67
     sacrific
    -0.65
     propos
    -0.62
     lifes
    -0.62
    natureconservancy
    -0.61
     bicycl
    -0.61
    ogy
    -0.61
     offic
    -0.60
     mete
    -0.60
    POSITIVE LOGITS
     Thumbnails
    1.02
     Mode
    0.92
     Content
    0.76
     IMAGES
    0.70
     Theatre
    0.69
     Enix
    0.69
     Curve
    0.66
    Container
    0.66
     Asylum
    0.65
     Featured
    0.65
    Activations Density 0.027%

    No Known Activations