© 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. 11486
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations or divisions

    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
    306
    +0.17
    0.9%
    136
    +0.13
    0.7%
    403
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.17
    0.04
    155
    +0.13
    0.02
    136
    +0.11
    -0.01
    Negative Logits
    ª
    -2.68
    į
    -2.52
    ²
    -2.52
    ·¸
    -2.50
    Īĺ
    -2.48
    ³
    -2.41
    ¾
    -2.41
    ¥
    -2.37
    ¿½
    -2.36
    µ
    -2.31
    POSITIVE LOGITS
     rue
    2.12
     Naples
    2.09
     Valencia
    2.06
     York
    2.05
     Orleans
    1.98
     Saint
    1.97
     south
    1.97
     justice
    1.96
    fered
    1.92
     East
    1.89
    Activations Density 0.180%

    No Known Activations