© 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 EvalsExportsinterp-engineNEWAPI 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. 24340
    Prev
    Next
    INDEX
    Explanations

    specific chemical compounds or biological terms

    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
    129
    +0.16
    0.9%
    396
    +0.12
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    129
    +0.16
    0.00
    372
    +0.12
    0.01
    410
    +0.12
    0.01
    Negative Logits
     behold
    -1.59
     forth
    -1.53
    PED
    -1.52
     finally
    -1.50
     viewed
    -1.48
    unnumbered
    -1.48
    OTAL
    -1.46
     dissemin
    -1.46
     entire
    -1.45
     recommending
    -1.42
    POSITIVE LOGITS
    ¬
    2.47
    ®
    2.43
    ¤
    2.38
    ¨
    2.34
    ¼
    2.29
    «
    2.19
    ¯
    2.14
    §
    2.12
    Ļ
    2.09
    ľ
    2.09
    Activations Density 0.065%

    No Known Activations