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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 5539
    Prev
    Next
    INDEX
    Explanations

    noun phrases related to fashion accessories

    oai_token-act-pair · gpt-3.5-turbo

    mentions of accessories and related items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zee
    -0.84
    teen
    -0.75
    rolled
    -0.75
    heit
    -0.72
    Arab
    -0.71
    hua
    -0.70
    \\\\\\\\
    -0.69
    bow
    -0.69
    76561
    -0.68
    ohan
    -0.68
    POSITIVE LOGITS
     accessory
    1.07
     accessories
    0.98
     peripher
    0.83
     Accessories
    0.80
     fitt
    0.78
     manufacturer
    0.75
     cables
    0.75
     retailer
    0.74
    Accessory
    0.73
     kit
    0.73
    Activations Density 0.024%

    No Known Activations