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. 387
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements or obligations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligations and requirements imposed by laws or regulations

    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
     Wim
    -0.79
    clips
    -0.70
    cffffcc
    -0.70
     Hits
    -0.68
    calling
    -0.67
    Notable
    -0.67
     Expansion
    -0.67
     Typ
    -0.65
    ////////////////////////////////
    -0.65
     intrig
    -0.64
    POSITIVE LOGITS
     comply
    1.60
     disclose
    1.58
     notify
    1.44
     obey
    1.44
     abide
    1.43
     submit
    1.41
     adhere
    1.40
     certify
    1.28
     furnish
    1.26
     undergo
    1.25
    Activations Density 0.155%

    No Known Activations