© 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. 2-RES-JB
    11. 12821
    Prev
    Next
    INDEX
    Explanations

    references to a pair of objects or individuals

    oai_token-act-pair · gpt-3.5-turbo

    the word "pair" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulhu
    -1.03
    ugu
    -0.75
    veyard
    -0.70
    avez
    -0.70
    ICLE
    -0.69
    UGE
    -0.64
    vernment
    -0.64
    pmwiki
    -0.64
    Interstitial
    -0.62
    ancock
    -0.62
    POSITIVE LOGITS
    pair
    1.09
     pair
    0.95
     pairs
    0.84
    rings
    0.84
     mates
    0.81
     halves
    0.81
    ably
    0.81
    wise
    0.78
    isons
    0.77
     Pair
    0.77
    Activations Density 0.008%

    No Known Activations