© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 13141
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions that convey the concept of examples or illustrations

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    307
    +0.16
    0.9%
    58
    +0.14
    0.8%
    337
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    182
    +0.16
    0.03
    497
    +0.14
    0.01
    252
    +0.14
    0.01
    Negative Logits
    soever
    -1.75
    istes
    -1.71
    doms
    -1.61
    ists
    -1.59
    GFR
    -1.58
    ishops
    -1.55
    **~
    -1.55
    lords
    -1.49
    laughs
    -1.48
    **]{}
    -1.46
    POSITIVE LOGITS
     my
    2.48
    ķ
    2.41
     fiddle
    2.15
     example
    2.05
    fiddle
    2.02
    ĺ
    2.01
     screenshot
    2.00
     code
    2.00
     html
    1.98
    µ
    1.98
    Activations Density 0.066%

    No Known Activations