© 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. 25447
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Pluto" and its variations

    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
    156
    +0.25
    1.4%
    17
    +0.12
    0.7%
    38
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.25
    0.12
    271
    +0.12
    0.05
    156
    +0.11
    0.06
    Negative Logits
     revolution
    -1.38
     denominator
    -1.35
     interloc
    -1.34
     autom
    -1.29
     polynomials
    -1.26
     integration
    -1.25
    buntu
    -1.23
     efficiency
    -1.22
     IEEE
    -1.22
     RH
    -1.22
    POSITIVE LOGITS
    ĻĤ
    2.56
    Ļ
    1.88
    ĨĴ
    1.88
    ¼
    1.86
    »¿
    1.81
    Ħ
    1.80
    ½
    1.76
    Ĩ
    1.73
    ±
    1.73
    IJ
    1.65
    Activations Density 0.129%

    No Known Activations