© 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. 4-RES-SM
    11. 14379
    Prev
    Next
    INDEX
    Explanations

    emotions or sentiments expressed in narratives

    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
    +0.43
    3.0%
    306
    +0.21
    1.5%
    255
    +0.13
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.43
    0.16
    450
    +0.21
    0.14
    316
    +0.13
    0.16
    Negative Logits
    »¿
    -1.75
     distributions
    -1.58
    -1.52
    -1.52
    -1.52
    -1.52
         ↵
    -1.52
    <|outofrange|>
    -1.52
    -1.52
    ↵
    -1.52
    POSITIVE LOGITS
    Anyway
    1.79
    ======
    1.78
    posted
    1.70
    nice
    1.56
    mozilla
    1.54
    interesting
    1.52
    _>
    1.50
    really
    1.50
    ________________
    1.49
    pretty
    1.49
    Activations Density 0.755%

    No Known Activations