© 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. 2-RES-SM
    11. 10495
    Prev
    Next
    INDEX
    Explanations

    endings associated with concluding statements or closure

    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
    108
    +0.14
    0.8%
    307
    +0.13
    0.8%
    265
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.14
    0.01
    307
    +0.13
    0.02
    10
    +0.11
    0.02
    Negative Logits
    monella
    -1.64
    elves
    -1.58
    ilate
    -1.53
    qui
    -1.46
     nullptr
    -1.45
    npmjs
    -1.44
    ql
    -1.41
    cause
    -1.40
    dern
    -1.38
    ACK
    -1.37
    POSITIVE LOGITS
    angered
    2.11
    azole
    1.93
    othelial
    1.91
    ocrine
    1.82
    verte
    1.80
    encies
    1.73
    ments
    1.71
    urance
    1.69
    ellation
    1.68
    rile
    1.63
    Activations Density 0.115%

    No Known Activations