© 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. 2-RES-SM
    11. 12900
    Prev
    Next
    INDEX
    Explanations

    negative sentiments related to love and relationships

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    235
    +0.14
    0.8%
    369
    +0.12
    0.7%
    220
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.14
    0.27
    111
    +0.12
    0.23
    71
    +0.11
    0.24
    Negative Logits
    ¼
    -2.34
    ¸
    -2.00
    ´
    -1.68
    ł
    -1.62
    ĥ
    -1.61
    ↵
    -1.54
    <|outofrange|>
    -1.54
    -1.54
    -1.54
    -1.54
    POSITIVE LOGITS
     <-
    2.08
    $]{};
    1.74
    :`
    1.61
    ))$.
    1.60
     INFO
    1.60
    |$.
    1.60
    ="#
    1.56
    !(
    1.52
     ::
    1.49
    _"
    1.48
    Activations Density 3.561%

    No Known Activations