© 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. 2-RES-SM
    11. 11601
    Prev
    Next
    INDEX
    Explanations

    phrases related to commercial transactions and location-based services

    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
    231
    +0.12
    0.6%
    198
    +0.10
    0.6%
    35
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.12
    0.07
    162
    +0.10
    0.08
    55
    +0.10
    0.07
    Negative Logits
    ¯
    -1.70
     ash
    -1.69
    )].
    -1.62
     myself
    -1.58
    ĥ½
    -1.58
    ´
    -1.55
    :&
    -1.53
    µ
    -1.53
    ¦
    -1.52
    ı
    -1.49
    POSITIVE LOGITS
    dating
    1.74
    going
    1.64
    :`
    1.57
    tes
    1.56
    ---|
    1.56
    worthy
    1.54
    glass
    1.51
    amazon
    1.51
    watson
    1.50
    recht
    1.48
    Activations Density 0.792%

    No Known Activations