© 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. 1-RES-SM
    11. 26039
    Prev
    Next
    INDEX
    Explanations

    conditional statements and exceptions related to travel regulations

    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
    478
    +0.14
    0.9%
    164
    +0.13
    0.8%
    162
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.08
    129
    +0.13
    0.03
    266
    +0.11
    0.06
    Negative Logits
    ically
    -1.58
     carriers
    -1.58
    gens
    -1.52
    itals
    -1.51
     carrier
    -1.43
    ).)
    -1.42
    ström
    -1.41
    jax
    -1.41
    iques
    -1.40
    engers
    -1.37
    POSITIVE LOGITS
    Ĥ
    3.16
    ĥ½
    2.80
    ĭ
    2.78
    »
    2.71
    ľĵ
    2.70
    º
    2.43
    ŀ
    2.40
    ı
    2.38
    ľ
    2.36
    ©
    2.32
    Activations Density 0.632%

    No Known Activations