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. 6-RES-JB
    6. 8765
    Prev
    Next
    INDEX
    Explanations

    verbs related to enforcement or implementation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "impose" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igi
    -0.69
     Bethlehem
    -0.67
    imeo
    -0.66
    bery
    -0.62
     Emin
    -0.61
    adelphia
    -0.61
    onge
    -0.61
    say
    -0.60
    ovies
    -0.60
     occasion
    -0.59
    POSITIVE LOGITS
     stricter
    1.02
     restrictive
    0.80
     strict
    0.80
     stringent
    0.79
     compulsory
    0.78
     draconian
    0.77
     unilaterally
    0.76
     clauses
    0.76
     unilateral
    0.75
     norms
    0.75
    Activations Density 0.174%

    No Known Activations