© 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. 1-RES-SM
    11. 29277
    Prev
    Next
    INDEX
    Explanations

    the word "we" in contexts suggesting collaboration or shared experiences

    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
    56
    +0.14
    0.8%
    120
    +0.12
    0.7%
    495
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.14
    0.00
    165
    +0.12
    0.00
    89
    +0.12
    0.00
    Negative Logits
    ){#
    -1.80
    leigh
    -1.67
    elian
    -1.66
    esan
    -1.60
    etted
    -1.44
    edic
    -1.43
    .=
    -1.42
    emis
    -1.39
    esa
    -1.34
    ftime
    -1.33
    POSITIVE LOGITS
    eries
    2.01
     hell
    1.66
    ations
    1.47
    props
    1.45
     hur
    1.45
    below
    1.32
     manageable
    1.31
    ÑģÑĤÑĮ
    1.31
    enough
    1.30
    оÑĩ
    1.30
    Activations Density 0.000%

    No Known Activations