© 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. 30003
    Prev
    Next
    INDEX
    Explanations

    references to the state of New York

    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
    457
    +0.15
    0.9%
    410
    +0.15
    0.8%
    248
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.15
    0.06
    423
    +0.15
    0.05
    30
    +0.13
    0.05
    Negative Logits
    acial
    -1.90
     completion
    -1.83
    eeper
    -1.51
     progression
    -1.50
     absence
    -1.47
     obstruction
    -1.44
     exhaustion
    -1.44
     certain
    -1.43
    oused
    -1.42
     strict
    -1.42
    POSITIVE LOGITS
    ±
    3.08
    ¾
    3.00
    Ħ
    2.90
    ŀ
    2.75
    ²
    2.61
    ¬
    2.58
    ħ
    2.54
    ł
    2.50
    ·¸
    2.47
    ĨĴ
    2.42
    Activations Density 0.080%

    No Known Activations