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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1150
    Prev
    Next
    INDEX
    Explanations

    instances where the word "counterparts" is mentioned in relation to comparing different entities or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to comparative entities or groups, particularly using terms like "counterparts" and "predecessors."

    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
    ute
    -0.56
    ruction
    -0.55
    otin
    -0.54
    ogged
    -0.54
     creek
    -0.53
     disputed
    -0.53
    race
    -0.52
     blame
    -0.52
    rina
    -0.52
     voted
    -0.51
    POSITIVE LOGITS
     counterparts
    3.92
     equivalents
    2.20
     counterpart
    2.17
     predecessors
    1.98
     peers
    1.90
     cousins
    1.75
     brethren
    1.74
     colleagues
    1.68
     contemporaries
    1.58
     successors
    1.50
    Activations Density 0.014%

    No Known Activations