© 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. 26692
    Prev
    Next
    INDEX
    Explanations

    function calls related to data retrieval

    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
    352
    +0.12
    0.7%
    53
    +0.12
    0.7%
    214
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.12
    0.04
    497
    +0.12
    0.03
    53
    +0.11
    0.05
    Negative Logits
    ingo
    -1.87
    ism
    -1.71
    ison
    -1.68
    rant
    -1.66
    garten
    -1.65
    iscus
    -1.63
    unto
    -1.60
    gar
    -1.59
    itsu
    -1.57
    hip
    -1.55
    POSITIVE LOGITS
     rid
    1.90
    ter
    1.73
    aways
    1.68
     away
    1.59
    ters
    1.58
     odds
    1.49
     acquainted
    1.49
     Away
    1.46
     updated
    1.43
     Info
    1.40
    Activations Density 0.147%

    No Known Activations