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. 7-RES-JB
    6. 9183
    Prev
    Next
    INDEX
    Explanations

    verbs related to reacting or reactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "react" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -0.88
    holder
    -0.76
    berman
    -0.66
    luster
    -0.62
     Angola
    -0.62
    holding
    -0.58
     Starr
    -0.57
     Mandela
    -0.57
     Anthem
    -0.57
    gow
    -0.57
    POSITIVE LOGITS
    ivated
    1.05
    ivity
    0.99
    ivating
    0.98
    ivation
    0.97
    itect
    0.96
    agen
    0.84
    ency
    0.84
    icum
    0.84
    angel
    0.83
    ivities
    0.82
    Activations Density 0.025%

    No Known Activations