© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14115
    Prev
    Next
    INDEX
    Explanations

    various forms of proper nouns and specific names

    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
    59
    +0.15
    0.9%
    199
    +0.14
    0.8%
    266
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.08
    348
    +0.14
    0.09
    18
    +0.12
    0.07
    Negative Logits
    IFIC
    -1.93
    ESULT
    -1.87
    efore
    -1.68
    FPar
    -1.66
    ationally
    -1.58
    ODUCTION
    -1.57
     msgid
    -1.57
    oretical
    -1.57
    80211
    -1.44
    otypical
    -1.43
    POSITIVE LOGITS
    ŀ
    2.35
    ¯
    2.34
    Ŀ
    2.29
    ī
    2.25
    ¹
    2.22
    ´
    2.19
    »¿
    2.18
    «
    2.14
    ©
    2.12
    ¡
    2.12
    Activations Density 0.947%

    No Known Activations