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. 3-RES-JB
    6. 7644
    Prev
    Next
    INDEX
    Explanations

    phrases related to accessories, both in a literal and metaphorical sense

    oai_token-act-pair · gpt-3.5-turbo

    references to 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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kern
    -0.75
    zee
    -0.74
    awar
    -0.69
    uman
    -0.66
    arching
    -0.64
    rolled
    -0.64
    hua
    -0.64
    zi
    -0.63
    ohan
    -0.63
    xious
    -0.63
    POSITIVE LOGITS
     accessories
    1.17
     accessory
    1.15
     Accessories
    0.98
     peripher
    0.88
    MpServer
    0.81
    Accessory
    0.81
     fitt
    0.78
     adapters
    0.78
     retailer
    0.77
     gadget
    0.76
    Activations Density 0.012%

    No Known Activations