© 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. 2-RES-SM
    11. 31625
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations and their attributes

    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
    410
    +0.12
    0.7%
    156
    +0.12
    0.7%
    8
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.12
    0.05
    251
    +0.12
    0.03
    30
    +0.11
    0.02
    Negative Logits
    Ħ
    -2.71
    Ĥ
    -2.61
    ĺ
    -2.54
    ľ
    -2.52
    ĨĴ
    -2.51
    ²
    -2.47
    Ģ
    -2.41
    Ĩ
    -2.38
    ¥
    -2.38
    ĸ
    -2.37
    POSITIVE LOGITS
    shire
    2.70
    hurst
    2.39
    wood
    1.88
    icense
    1.84
    ford
    1.64
    ffield
    1.64
    stown
    1.63
     area
    1.60
    vist
    1.59
    bour
    1.53
    Activations Density 0.211%

    No Known Activations