© 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. 25675
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations, particularly counties and shires

    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
    156
    +0.19
    1.1%
    503
    +0.13
    0.7%
    58
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.19
    0.05
    156
    +0.13
    0.03
    271
    +0.11
    0.01
    Negative Logits
    ij
    -2.35
    ĺ
    -2.31
    ¤
    -2.25
    Īĺ
    -2.19
    Ĺ
    -2.16
    Ķ
    -2.13
    ł
    -2.13
    ĵ
    -2.11
    Ĥ
    -2.06
    ·
    -2.03
    POSITIVE LOGITS
    vist
    2.12
    hurst
    1.91
     area
    1.78
     sights
    1.67
    selves
    1.66
    entes
    1.64
    icum
    1.62
    shire
    1.62
    creen
    1.60
    ian
    1.58
    Activations Density 0.209%

    No Known Activations