© 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. 30990
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a high level of demand across various contexts

    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
    354
    +0.14
    0.8%
    335
    +0.12
    0.7%
    186
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.14
    0.04
    354
    +0.12
    0.03
    186
    +0.11
    0.02
    Negative Logits
    à±ģ
    -1.99
    ĻĤ
    -1.98
    ¿½
    -1.82
    à±į
    -1.68
    à±
    -1.66
    áĢº
    -1.60
     eds
    -1.56
    £
    -1.54
    rish
    -1.52
    áĢ¯
    -1.49
    POSITIVE LOGITS
     stric
    1.83
    ive
    1.82
    ência
    1.75
    ering
    1.74
    ence
    1.73
    iest
    1.71
    vers
    1.56
    ant
    1.54
     imposed
    1.54
     tolerant
    1.53
    Activations Density 0.243%

    No Known Activations