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. 5989
    Prev
    Next
    INDEX
    Explanations

    sentences emphasizing accountability and responsibility toward law enforcement actions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express finality or closure

    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
    thal
    -0.95
     ransom
    -0.80
     sleeper
    -0.78
     dracon
    -0.77
    IRE
    -0.73
     embargo
    -0.72
     libel
    -0.72
     treason
    -0.70
     canon
    -0.69
    inally
    -0.69
    POSITIVE LOGITS
     Eventually
    1.15
     Occasionally
    1.11
     Residents
    1.11
     Dozens
    1.09
     Visitors
    1.09
     Along
    1.08
     Sitting
    1.08
     Sometimes
    1.06
     But
    1.06
     Instead
    1.01
    Activations Density 0.527%

    No Known Activations