© 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. 1-RES-SM
    11. 25043
    Prev
    Next
    INDEX
    Explanations

    references to "Dream" in various contexts, indicating a focus on aspirations or ideals

    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
    498
    +0.14
    0.8%
    59
    +0.13
    0.7%
    444
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.03
    144
    +0.13
    0.03
    58
    +0.13
    0.02
    Negative Logits
    gered
    -1.64
    ylum
    -1.55
    omnia
    -1.51
     bans
    -1.49
    pto
    -1.46
    apine
    -1.46
    illon
    -1.45
    amyl
    -1.42
    remia
    -1.41
     giants
    -1.38
    POSITIVE LOGITS
    s
    2.24
    sburg
    1.87
    nie
    1.87
    stown
    1.74
    emann
    1.73
    son
    1.72
    sie
    1.72
     Elementary
    1.71
    owitz
    1.68
    ska
    1.67
    Activations Density 0.476%

    No Known Activations