© 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. 8951
    Prev
    Next
    INDEX
    Explanations

    phrases expressing strong emotional reactions or exclamations

    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
    266
    +0.12
    0.7%
    271
    +0.12
    0.6%
    505
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.12
    0.04
    390
    +0.12
    0.12
    481
    +0.11
    0.10
    Negative Logits
    Ļ
    -4.09
    -4.03
    č↵
    -4.03
    -4.03
    ↵
    -4.03
    -4.03
    <|outofrange|>
    -4.03
    ↵
    -4.03
    <|outofrange|>
    -4.03
    ↵
    -4.03
    POSITIVE LOGITS
    !
    5.65
    !!
    5.23
    !!!
    4.77
    !(
    4.64
    ?!
    4.53
    !!!!
    4.50
    !)
    4.48
    !\
    4.46
    !”
    4.41
    !_
    4.29
    Activations Density 2.590%

    No Known Activations