© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 13662
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with age

    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
    217
    +0.14
    0.8%
    169
    +0.11
    0.6%
    302
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.14
    0.02
    217
    +0.11
    0.03
    503
    +0.10
    0.02
    Negative Logits
    \)
    -1.70
     arbitrary
    -1.50
    s
    -1.45
     else
    -1.41
    pton
    -1.41
     anything
    -1.39
    sel
    -1.38
    rid
    -1.36
    ness
    -1.35
    sen
    -1.33
    POSITIVE LOGITS
    vity
    1.90
    grounds
    1.88
    ogens
    1.64
    rer
    1.62
    ing
    1.58
    ress
    1.56
    egan
    1.56
    hog
    1.53
    ability
    1.52
     Area
    1.50
    Activations Density 0.167%

    No Known Activations