© 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. 27780
    Prev
    Next
    INDEX
    Explanations

    statements about improving systems and processes for better outcomes

    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
    49
    +0.19
    1.1%
    73
    +0.18
    1.0%
    233
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    73
    +0.19
    0.07
    287
    +0.18
    0.09
    49
    +0.14
    0.09
    Negative Logits
    ĻĤ
    -3.51
    Į
    -2.73
    ¿½
    -2.66
    ·
    -2.60
    Ī
    -2.59
    ¸
    -2.56
    Ĥ¬
    -2.55
    ·¸
    -2.55
    ij
    -2.55
    Ħ
    -2.52
    POSITIVE LOGITS
    ?’
    1.95
    ?'
    1.75
    dry
    1.72
    itro
    1.67
     crawl
    1.65
     ourselves
    1.63
    ILY
    1.57
    ()),
    1.50
    istine
    1.49
     tune
    1.49
    Activations Density 1.266%

    No Known Activations