© 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. 28672
    Prev
    Next
    INDEX
    Explanations

    instances of the word "until"

    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
    478
    +0.22
    1.2%
    376
    +0.14
    0.8%
    115
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.22
    0.04
    191
    +0.14
    0.03
    168
    +0.14
    0.03
    Negative Logits
    eer
    -1.63
    groupId
    -1.56
    Interface
    -1.48
    liche
    -1.46
    ceral
    -1.43
    ele
    -1.39
    face
    -1.38
    eno
    -1.37
    HT
    -1.36
    friendly
    -1.36
    POSITIVE LOGITS
     now
    1.55
     grateful
    1.55
     else
    1.53
    ndef
    1.49
     unwilling
    1.48
     elif
    1.47
     referee
    1.47
     departing
    1.45
     unsure
    1.44
     regret
    1.43
    Activations Density 0.342%

    No Known Activations