© 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 EvalsExportsAPI 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. 11067
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations, particularly towns and counties in Pennsylvania and New Jersey

    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
    78
    +0.15
    0.9%
    415
    +0.12
    0.7%
    9
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    131
    +0.15
    0.04
    21
    +0.12
    0.02
    373
    +0.11
    0.04
    Negative Logits
    ·¸
    -2.85
    ³
    -2.74
    ĭ
    -2.53
    ĥ½
    -2.47
    Ĺ
    -2.42
    ¼
    -2.34
    ¿
    -2.34
    ĨĴ
    -2.33
    º
    -2.31
    į
    -2.23
    POSITIVE LOGITS
     Township
    2.25
     Arkansas
    2.19
     Pennsylvania
    2.16
     Delaware
    2.11
     Wyoming
    2.08
     counties
    2.08
     Kansas
    2.08
     Indiana
    2.04
     County
    1.97
     Mississippi
    1.96
    Activations Density 0.239%

    No Known Activations