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. 10-RES-JB
    6. 17633
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or states of being

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olitics
    -0.73
    owan
    -0.72
    ancies
    -0.68
    iences
    -0.68
    atives
    -0.67
     expire
    -0.66
     belongs
    -0.66
     Matter
    -0.65
     Liberties
    -0.65
    =-=-
    -0.64
    POSITIVE LOGITS
     attempting
    1.38
     proposing
    1.35
     employing
    1.31
     creating
    1.30
     trying
    1.29
     doing
    1.29
     constructing
    1.29
     putting
    1.28
     introducing
    1.28
     using
    1.27
    Activations Density 0.397%

    No Known Activations