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. 4-RES-JB
    6. 21378
    Prev
    Next
    INDEX
    Explanations

    mentions or occurrences of the term "inception"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of 'inception'

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

    No Comments

    Negative Logits
    hov
    -0.68
     explorers
    -0.66
     sink
    -0.65
     conscience
    -0.63
    han
    -0.63
    oke
    -0.63
     unloaded
    -0.62
     harbor
    -0.61
     bath
    -0.60
     paddle
    -0.60
    POSITIVE LOGITS
    ptives
    0.88
    ptive
    0.85
    adjusted
    0.85
    sembly
    0.85
    WAYS
    0.82
    mination
    0.81
    daq
    0.79
    terness
    0.79
    date
    0.77
    rity
    0.77
    Activations Density 0.037%

    No Known Activations