© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11819
    Prev
    Next
    INDEX
    Explanations

    instances of moral or ethical dilemmas involving characters in complex situations

    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
    186
    +0.19
    1.1%
    156
    +0.16
    0.9%
    56
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    186
    +0.19
    0.19
    56
    +0.16
    0.07
    117
    +0.15
    0.17
    Negative Logits
    -5.42
    č↵
    -5.42
    ↵↵
    -5.42
              ↵
    -5.42
    ↵
    -5.42
    <|outofrange|>
    -5.42
    -5.42
    <|outofrange|>
    -5.42
    ↵
    -5.42
    -5.42
    POSITIVE LOGITS
    ?!
    2.20
     shit
    2.14
     hell
    2.05
     someday
    2.01
    ?).
    2.00
     fuck
    1.95
     theirs
    1.91
    ?)
    1.90
    ???
    1.89
     fucking
    1.88
    Activations Density 6.596%

    No Known Activations