© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26360
    Prev
    Next
    INDEX
    Explanations

    punctuation that concludes sentences

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    60
    +0.15
    0.9%
    390
    +0.14
    0.8%
    160
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.15
    0.00
    23
    +0.14
    0.00
    248
    +0.12
    0.00
    Negative Logits
    ayer
    -1.76
    enstein
    -1.72
    ikov
    -1.63
    anan
    -1.59
    Å¡ÃŃ
    -1.58
    horn
    -1.58
    liner
    -1.57
    sep
    -1.57
     testament
    -1.56
    roup
    -1.56
    POSITIVE LOGITS
    shire
    1.57
     scientists
    1.51
    phantom
    1.45
     ballistic
    1.37
     copies
    1.35
     fingers
    1.35
     candidates
    1.35
    eous
    1.34
    grams
    1.33
     abuse
    1.32
    Activations Density 0.000%

    No Known Activations