© 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. 1-RES-SM
    11. 25753
    Prev
    Next
    INDEX
    Explanations

    the word "upon" in various contexts

    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
    +0.15
    0.8%
    148
    +0.14
    0.8%
    69
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.15
    0.03
    344
    +0.14
    0.02
    328
    +0.12
    0.02
    Negative Logits
    astolic
    -1.51
    etus
    -1.48
    ucleotide
    -1.45
    ¯
    -1.45
    "}](#
    -1.44
    encia
    -1.43
    ADS
    -1.43
    etal
    -1.42
    ĸ
    -1.41
    AD
    -1.39
    POSITIVE LOGITS
     firing
    1.69
     resignation
    1.65
     retiring
    1.57
     ret
    1.46
     discovery
    1.43
     killing
    1.41
     resent
    1.39
     spraying
    1.38
     exterior
    1.38
     returning
    1.38
    Activations Density 0.144%

    No Known Activations