© 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. 1-RES-SM
    11. 29998
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    53
    +0.15
    0.9%
    269
    +0.15
    0.9%
    225
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.15
    0.11
    53
    +0.15
    0.18
    271
    +0.14
    0.04
    Negative Logits
    cript
    -1.64
    illery
    -1.60
    omyc
    -1.46
    omi
    -1.44
    .\[[@
    -1.43
     Pharmac
    -1.36
    ↵↵↵↵
    -1.35
    asia
    -1.35
     Ms
    -1.35
    icals
    -1.33
    POSITIVE LOGITS
    Ĵ
    2.03
    ·¸
    1.81
    ¾
    1.75
    §
    1.64
    ¬
    1.59
    »¿
    1.59
    ¶
    1.50
    ´
    1.46
    ↵↵
    1.44
    ↵
    1.44
    Activations Density 1.757%

    No Known Activations