© 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. 27587
    Prev
    Next
    INDEX
    Explanations

    references to copyright and licensing 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/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
    87
    +0.12
    0.7%
    290
    +0.11
    0.6%
    131
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.12
    0.02
    290
    +0.11
    0.02
    131
    +0.11
    0.01
    Negative Logits
    ¢
    -3.47
    ²
    -3.35
    °
    -3.21
    ı
    -3.17
    ·
    -3.15
    ¦
    -3.13
    ´
    -3.13
    Ĥ¬
    -3.11
    ®
    -3.10
    Ł
    -3.06
    POSITIVE LOGITS
    ublic
    1.67
    licenses
    1.62
    sson
    1.57
    ptions
    1.55
    mitt
    1.53
    fficients
    1.47
    scape
    1.47
     remains
    1.46
     infringement
    1.44
    smen
    1.44
    Activations Density 0.028%

    No Known Activations