© 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. 30399
    Prev
    Next
    INDEX
    Explanations

    references to personal possession or ownership

    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
    10
    +0.12
    0.7%
    369
    +0.12
    0.7%
    478
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.12
    0.08
    385
    +0.12
    0.06
    230
    +0.12
    0.04
    Negative Logits
    ructure
    -1.81
    ening
    -1.72
    anto
    -1.62
    emann
    -1.57
    à«ĩ
    -1.54
    ener
    -1.53
    enes
    -1.51
    à°¿
    -1.50
    ened
    -1.48
    aside
    -1.47
    POSITIVE LOGITS
     own
    3.14
     favorite
    2.40
     favourite
    2.10
     Own
    2.05
     instincts
    1.86
     liking
    1.84
     friend
    1.82
     friends
    1.79
    self
    1.79
     feet
    1.79
    Activations Density 0.253%

    No Known Activations