© 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. 14126
    Prev
    Next
    INDEX
    Explanations

    financial figures and budget information

    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
    17
    +0.18
    1.1%
    186
    +0.14
    0.8%
    24
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.18
    0.02
    104
    +0.14
    0.05
    157
    +0.14
    0.08
    Negative Logits
    µ
    -2.48
    Ł
    -2.40
    Ħ
    -2.39
    ł
    -2.36
    ´
    -2.35
    ¼
    -2.33
    ¾
    -2.32
    Ĭ
    -2.32
    ħ
    -2.30
    į
    -2.28
    POSITIVE LOGITS
    ---|---
    1.82
    ---|---|---
    1.80
    "|
    1.67
    ingale
    1.59
    ierno
    1.52
    ---|
    1.46
    \%
    1.46
    +$
    1.43
    {.
    1.43
     appropri
    1.41
    Activations Density 1.377%

    No Known Activations