© 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. 13137
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "many" and its variations indicating quantity

    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
    466
    +0.15
    0.8%
    284
    +0.12
    0.7%
    125
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.15
    0.06
    284
    +0.12
    0.04
    32
    +0.12
    0.04
    Negative Logits
    ¯
    -1.64
    lique
    -1.60
    etype
    -1.59
    xico
    -1.50
    ulance
    -1.50
    imab
    -1.48
    ancement
    -1.48
    escence
    -1.48
    iona
    -1.47
    esse
    -1.45
    POSITIVE LOGITS
     others
    2.30
     occasions
    2.24
     kinds
    2.23
     facets
    2.21
     people
    2.21
     times
    2.21
     different
    2.16
     years
    2.11
     aspects
    2.09
     ways
    2.07
    Activations Density 0.211%

    No Known Activations