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. 2-RES-JB
    6. 20347
    Prev
    Next
    INDEX
    Explanations

    instances where the word "share" is used

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "share" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.83
     desper
    -0.75
     submar
    -0.67
     streng
    -0.63
     robbed
    -0.62
    judicial
    -0.62
     overth
    -0.62
     reper
    -0.61
     srf
    -0.61
     cumbers
    -0.61
    POSITIVE LOGITS
    cro
    1.09
    holders
    0.97
    holder
    0.88
     share
    0.85
    ership
    0.84
    hare
    0.82
    holding
    0.81
     Share
    0.81
     shares
    0.80
     Shares
    0.74
    Activations Density 0.024%

    No Known Activations