© 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. 26253
    Prev
    Next
    INDEX
    Explanations

    references to software licenses

    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
    499
    +0.13
    0.7%
    114
    +0.11
    0.6%
    169
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.13
    0.02
    114
    +0.11
    0.02
    469
    +0.10
    0.02
    Negative Logits
    ľĵ
    -2.43
    ij
    -2.40
    ´
    -2.22
    Ĺ
    -2.22
    ®
    -2.22
    Ĥ¬
    -2.19
    ²
    -2.17
    ·
    -2.16
    »
    -2.14
    ļ
    -2.11
    POSITIVE LOGITS
    alore
    1.66
    ense
    1.52
     jur
    1.51
    ymphony
    1.48
    icense
    1.48
    ousand
    1.48
    ación
    1.47
    ftware
    1.44
    licenses
    1.44
    amiento
    1.43
    Activations Density 0.085%

    No Known Activations