© 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. 4-RES-SM
    11. 12435
    Prev
    Next
    INDEX
    Explanations

    terms related to automation and automated processes in business 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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    21
    +0.20
    1.2%
    405
    +0.15
    0.9%
    203
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.20
    0.02
    203
    +0.15
    0.02
    405
    +0.13
    0.02
    Negative Logits
    hene
    -1.80
    itud
    -1.66
    htra
    -1.62
     likelihood
    -1.56
     aloud
    -1.53
    fully
    -1.47
    holds
    -1.44
    resses
    -1.37
     quo
    -1.36
    lections
    -1.35
    POSITIVE LOGITS
    otive
    2.60
    obiles
    2.36
    ķ
    2.23
    obile
    2.21
    atically
    2.09
    ĵ
    2.05
    ount
    2.04
    ı
    2.02
    ½
    1.91
    aton
    1.89
    Activations Density 0.170%

    No Known Activations