© 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. 29048
    Prev
    Next
    INDEX
    Explanations

    instances of the word "successfully."

    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
    +0.17
    1.0%
    376
    +0.14
    0.8%
    51
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.17
    0.02
    300
    +0.14
    0.02
    199
    +0.14
    0.02
    Negative Logits
    ler
    -1.71
    way
    -1.65
    rie
    -1.65
    lessness
    -1.63
    ways
    -1.63
    aurus
    -1.62
    ter
    -1.59
    isa
    -1.58
     matter
    -1.58
    liche
    -1.54
    POSITIVE LOGITS
     enough
    1.84
    ĻĤ
    1.70
    sembled
    1.39
    ¤
    1.38
     yours
    1.36
    EVER
    1.31
     mob
    1.31
     conver
    1.31
     firing
    1.30
     neut
    1.28
    Activations Density 0.059%

    No Known Activations