© 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. 25049
    Prev
    Next
    INDEX
    Explanations

    phrases indicating knowledge, understanding, or awareness followed by actions related to decision-making or expectations

    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
    23
    +0.24
    1.4%
    338
    +0.12
    0.7%
    82
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    435
    +0.24
    0.07
    348
    +0.12
    0.09
    23
    +0.11
    0.09
    Negative Logits
    erals
    -1.90
     (“
    -1.78
    osto
    -1.71
    ļ
    -1.69
    ĩ
    -1.63
    ritis
    -1.58
    oddsidemargin
    -1.56
    §
    -1.54
    rition
    -1.53
    unct
    -1.50
    POSITIVE LOGITS
     Lady
    1.82
     both
    1.79
    ighs
    1.54
     sign
    1.48
     dual
    1.47
    ]{.
    1.46
     fetal
    1.46
     always
    1.44
     bir
    1.43
     reception
    1.42
    Activations Density 1.202%

    No Known Activations