© 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. 25610
    Prev
    Next
    INDEX
    Explanations

    terms related to types of cancer and their characteristics

    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
    +0.23
    1.4%
    17
    +0.20
    1.2%
    111
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.23
    0.15
    347
    +0.20
    0.09
    71
    +0.13
    0.14
    Negative Logits
     sino
    -1.66
    )."
    -1.53
     parte
    -1.40
    imer
    -1.35
    .[@
    -1.35
    .^[@
    -1.33
     Briefly
    -1.32
     Univers
    -1.31
     ([@
    -1.31
     Moscow
    -1.30
    POSITIVE LOGITS
    ģ
    1.99
    ĺ
    1.98
    ĻĤ
    1.97
    Ĺ
    1.93
    Ļª
    1.76
    °
    1.75
    ´
    1.71
    ¡
    1.70
    Į
    1.69
    Ĩ
    1.68
    Activations Density 2.814%

    No Known Activations