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

    Neuronpedia

    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. 11139
    Prev
    Next
    INDEX
    Explanations

    geographic locations and regional identifiers

    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
    362
    +0.19
    1.1%
    156
    +0.18
    1.0%
    438
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.19
    0.03
    145
    +0.18
    0.03
    445
    +0.17
    0.02
    Negative Logits
    OLOG
    -1.69
    inous
    -1.56
    raise
    -1.52
    ionate
    -1.47
    APH
    -1.46
    atically
    -1.44
    tes
    -1.43
    fulness
    -1.42
    ptions
    -1.41
     quantitatively
    -1.40
    POSITIVE LOGITS
     provinces
    1.86
     leagues
    1.76
     counties
    1.76
     suburbs
    1.70
    ¿½
    1.66
    ised
    1.62
     towns
    1.59
     states
    1.58
     cities
    1.58
    ´
    1.56
    Activations Density 0.132%

    No Known Activations