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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 29337
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Bor" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    369
    +0.18
    1.0%
    443
    +0.15
    0.8%
    504
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.18
    0.03
    59
    +0.15
    0.02
    71
    +0.14
    0.03
    Negative Logits
    ļ
    -1.84
    ľĵ
    -1.76
    ľ
    -1.69
     bas
    -1.53
    Ŀ
    -1.52
    ŀ
    -1.51
    ?>
    -1.48
    WORD
    -1.44
    Ń
    -1.42
    ¡
    -1.41
    POSITIVE LOGITS
    ishment
    2.15
    wick
    2.01
    owitz
    2.01
    isher
    1.96
    lands
    1.95
    ishes
    1.88
    oslov
    1.83
    icultural
    1.83
    nex
    1.83
    issance
    1.81
    Activations Density 0.097%

    No Known Activations