© 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. 4-RES-SM
    11. 9908
    Prev
    Next
    INDEX
    Explanations

    locations and entities related to geography and community infrastructure

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    25
    +0.14
    0.8%
    466
    +0.13
    0.7%
    48
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.14
    0.06
    216
    +0.13
    0.09
    48
    +0.12
    0.06
    Negative Logits
    ·¸
    -6.49
    ↵
    -6.25
    ↵↵↵
    -6.25
    -6.25
    -6.25
    -6.25
    <|outofrange|>
    -6.25
    č↵
    -6.25
    -6.25
    ↵
    -6.25
    POSITIVE LOGITS
     Mountains
    2.98
     Peninsula
    2.81
     Avenue
    2.77
     Island
    2.71
     peninsula
    2.65
     County
    2.64
     Road
    2.63
     Valley
    2.59
     Township
    2.55
     River
    2.54
    Activations Density 0.775%

    No Known Activations