© 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. 25373
    Prev
    Next
    INDEX
    Explanations

    references to seals and sealing processes in various contexts

    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
    156
    +0.17
    1.0%
    492
    +0.14
    0.8%
    306
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.17
    0.01
    275
    +0.14
    0.02
    306
    +0.13
    0.01
    Negative Logits
     sweat
    -1.56
     sudden
    -1.52
     rac
    -1.52
    lli
    -1.43
    *>
    -1.41
    elf
    -1.41
    downarrow
    -1.40
    sterdam
    -1.38
    asma
    -1.37
     vain
    -1.37
    POSITIVE LOGITS
    ĥ
    2.78
    ĻĤ
    2.59
    Ħ
    2.51
    ¢
    2.42
    ģ
    2.40
    Ī
    2.27
    Ļª
    2.24
    ¿
    2.19
    ī
    2.19
    ¿½
    2.17
    Activations Density 0.110%

    No Known Activations