© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27318
    Prev
    Next
    INDEX
    Explanations

    words associated with describing or categorizing subjects

    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
    156
    +0.24
    1.4%
    311
    +0.12
    0.7%
    100
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.24
    0.01
    126
    +0.12
    0.01
    38
    +0.12
    0.01
    Negative Logits
    unnumbered
    -1.74
    ż
    -1.61
    jours
    -1.51
    iamo
    -1.50
    vate
    -1.49
     YOU
    -1.42
    arning
    -1.40
    abouts
    -1.38
    onas
    -1.37
     PlayStation
    -1.36
    POSITIVE LOGITS
    arily
    1.86
    ally
    1.73
    istically
    1.65
    isms
    1.63
    ably
    1.60
    izes
    1.56
    etically
    1.56
    matically
    1.51
    aneously
    1.48
     minimizes
    1.47
    Activations Density 0.046%

    No Known Activations