© 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. 4-RES-SM
    11. 14848
    Prev
    Next
    INDEX
    Explanations

    variations of possessive pronouns and references to individuals' relationships

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    416
    +0.15
    0.8%
    149
    +0.14
    0.8%
    235
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    149
    +0.15
    0.08
    416
    +0.14
    0.07
    145
    +0.13
    0.05
    Negative Logits
    ±
    -2.94
    Ļ
    -2.82
    ij
    -2.79
    ĨĴ
    -2.59
    «
    -2.53
    §
    -2.52
    ·¸
    -2.51
    Ļª
    -2.49
    ł
    -2.48
    ĸ´
    -2.45
    POSITIVE LOGITS
     midst
    2.52
     entirety
    2.49
     infancy
    2.24
     own
    2.21
     haste
    2.14
     mind
    2.11
     hands
    2.08
     hometown
    2.02
     backyard
    1.98
     minds
    1.96
    Activations Density 0.363%

    No Known Activations