© 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. 31397
    Prev
    Next
    INDEX
    Explanations

    patterns related to structured data or coding formats

    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
    275
    +0.16
    0.9%
    240
    +0.13
    0.7%
    210
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.16
    0.04
    445
    +0.13
    0.03
    7
    +0.13
    -0.02
    Negative Logits
    doibase
    -1.81
     Photograph
    -1.41
    istar
    -1.39
    LAND
    -1.36
    à±ģ
    -1.36
    áĢ¬
    -1.35
     Suite
    -1.34
    àµ
    -1.29
    àµį
    -1.29
    rano
    -1.28
    POSITIVE LOGITS
    Īĺ
    1.75
    ĥ
    1.69
    Ĥ¬
    1.66
    imits
    1.59
     themselves
    1.58
    Ĭ
    1.56
    ĵ
    1.55
    ģ
    1.51
    ly
    1.49
    ĭ
    1.48
    Activations Density 5.840%

    No Known Activations