© 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. 2-RES-SM
    11. 9580
    Prev
    Next
    INDEX
    Explanations

    links and references to help guides or FAQs within forums

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    302
    +0.14
    0.8%
    315
    +0.11
    0.6%
    221
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    315
    +0.14
    0.03
    329
    +0.11
    0.02
    221
    +0.11
    0.02
    Negative Logits
    orphic
    -1.69
     tomography
    -1.52
    ucid
    -1.48
    ichia
    -1.48
    producing
    -1.47
    oretic
    -1.46
     natural
    -1.44
    ismic
    -1.43
    ÅŁ
    -1.42
    scill
    -1.42
    POSITIVE LOGITS
    ©
    2.68
    Ĵ
    2.53
    ¹
    2.51
    ·
    2.45
    ª
    2.34
    ¤
    2.33
    ĨĴ
    2.32
    ³
    2.31
    °
    2.31
    ij
    2.30
    Activations Density 0.345%

    No Known Activations