© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-SM
    11. 30241
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing dedication and commitment to a cause or organization

    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
    394
    +0.12
    0.6%
    144
    +0.11
    0.6%
    348
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.12
    0.02
    277
    +0.11
    0.03
    511
    +0.10
    0.01
    Negative Logits
    ÃŃas
    -1.65
    bery
    -1.54
    ses
    -1.40
    »
    -1.33
    ashed
    -1.32
    ĨĴ
    -1.31
    akh
    -1.31
    ħ
    -1.31
    que
    -1.31
    ikel
    -1.30
    POSITIVE LOGITS
    ness
    2.03
    erville
    1.64
    ence
    1.61
    izione
    1.59
    irector
    1.58
    lay
    1.48
     to
    1.48
    lif
    1.44
    endant
    1.42
    ition
    1.41
    Activations Density 0.184%

    No Known Activations