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. 3946
    Prev
    Next
    INDEX
    Explanations

    action verbs indicating taking some form of action

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to official decisions and regulatory measures

    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
    ooked
    -0.78
     Dying
    -0.77
    Brit
    -0.77
     busted
    -0.76
     hated
    -0.76
     hooked
    -0.73
    didn
    -0.73
     Crazy
    -0.73
    ihad
    -0.73
    Got
    -0.72
    POSITIVE LOGITS
     undertake
    1.55
     ensure
    1.46
     commence
    1.36
     provide
    1.31
     allocate
    1.29
     initiate
    1.29
     notify
    1.27
     assure
    1.27
     facilitate
    1.27
     comply
    1.27
    Activations Density 0.312%

    No Known Activations