© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 10514
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their distribution

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    98
    +0.21
    1.2%
    499
    +0.14
    0.8%
    422
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.21
    0.02
    362
    +0.14
    0.09
    95
    +0.13
    0.07
    Negative Logits
    ĻĤ
    -1.91
    Į
    -1.90
    ¥
    -1.85
    ²
    -1.76
    ĭ
    -1.62
     cured
    -1.57
    Ĺ
    -1.54
    intendent
    -1.54
    ĥ½
    -1.51
    «
    -1.51
    POSITIVE LOGITS
     division
    1.72
     departments
    1.68
     Asia
    1.64
     finance
    1.61
     kingdom
    1.59
     disciplines
    1.56
     society
    1.55
     region
    1.55
     divisions
    1.51
     vicinity
    1.50
    Activations Density 1.643%

    No Known Activations