© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 8238
    Prev
    Next
    INDEX
    Explanations

    instances where a particular person or thing is being compared to another person or thing

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "counterpart."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eters
    -0.67
    ute
    -0.63
    votes
    -0.60
    renches
    -0.58
     Beg
    -0.57
    Studio
    -0.57
    etc
    -0.56
    sudo
    -0.54
     Saw
    -0.54
     Et
    -0.53
    POSITIVE LOGITS
     counterpart
    4.06
     counterparts
    2.79
     predecessor
    1.96
     equivalents
    1.71
     predecessors
    1.63
     successor
    1.54
     equivalent
    1.41
     cousin
    1.34
     brethren
    1.23
     cousins
    1.19
    Activations Density 0.006%

    No Known Activations