© 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. 9933
    Prev
    Next
    INDEX
    Explanations

    terms associated with loss and deprivation

    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
    100
    +0.14
    0.8%
    467
    +0.14
    0.8%
    327
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.14
    0.02
    100
    +0.14
    0.02
    206
    +0.12
    0.01
    Negative Logits
     Parenthood
    -1.79
     Asst
    -1.59
    blogspot
    -1.54
    ="@
    -1.51
    ="@+
    -1.48
    thems
    -1.45
    renn
    -1.41
    utor
    -1.40
    typeof
    -1.33
    iasis
    -1.31
    POSITIVE LOGITS
    icity
    1.75
    ceral
    1.73
    ive
    1.67
     balance
    1.67
     occurred
    1.66
    ality
    1.66
    ously
    1.65
     zone
    1.65
    ight
    1.64
     occurring
    1.64
    Activations Density 0.106%

    No Known Activations