© 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. 13778
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, particularly those in Minnesota and Hungary

    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
    156
    +0.18
    1.0%
    369
    +0.17
    1.0%
    144
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.18
    0.07
    369
    +0.17
    0.03
    279
    +0.13
    0.04
    Negative Logits
    itance
    -1.83
    istant
    -1.76
     intervals
    -1.68
    acting
    -1.62
    izable
    -1.60
    igned
    -1.60
    cludes
    -1.59
    ferentially
    -1.55
    ateral
    -1.52
    onant
    -1.48
    POSITIVE LOGITS
     Lakes
    1.86
    town
    1.61
     Airlines
    1.60
     Institute
    1.53
    İ
    1.53
     States
    1.46
    ĸ
    1.44
    esota
    1.43
    obile
    1.41
     preserve
    1.41
    Activations Density 0.397%

    No Known Activations