© 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. 14177
    Prev
    Next
    INDEX
    Explanations

    assertive statements regarding statistical outcomes or conclusions

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    153
    +0.17
    1.0%
    419
    +0.17
    1.0%
    369
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.17
    0.07
    291
    +0.17
    0.12
    63
    +0.14
    0.07
    Negative Logits
     Cookies
    -1.54
     Suite
    -1.43
     Band
    -1.38
    iverse
    -1.34
     420
    -1.34
     Harbor
    -1.31
     etc
    -1.31
     honey
    -1.30
    ""
    -1.29
     Palm
    -1.26
    POSITIVE LOGITS
    3.21
    3.21
    <|outofrange|>
    3.21
    č↵
    3.21
     ↵
    3.21
    <|outofrange|>
    3.21
    <|outofrange|>
    3.21
    ↵
    3.21
    <|outofrange|>
    3.21
    ↵
    3.21
    Activations Density 8.480%

    No Known Activations