© 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. 1-RES-SM
    11. 26229
    Prev
    Next
    INDEX
    Explanations

    instances of the word "given" and its variations, emphasizing the concept of provision or receipt

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    376
    +0.13
    0.7%
    346
    +0.11
    0.6%
    230
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.13
    0.03
    236
    +0.11
    0.03
    185
    +0.10
    0.03
    Negative Logits
    µ
    -1.76
    Ļª
    -1.72
    nbsp
    -1.70
    blogger
    -1.63
    ¸
    -1.57
    "]
    -1.57
    ĨĴ
    -1.56
    ī
    -1.55
    ."_
    -1.54
    Ń
    -1.53
    POSITIVE LOGITS
    eful
    1.52
    ftware
    1.50
     trust
    1.45
     rise
    1.44
     answer
    1.38
     diet
    1.36
     deference
    1.36
     gravity
    1.35
     ordinal
    1.34
    ogue
    1.34
    Activations Density 0.095%

    No Known Activations