© 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. 1-RES-SM
    11. 24577
    Prev
    Next
    INDEX
    Explanations

    expressions of emotional states and feelings

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    396
    +0.12
    0.7%
    311
    +0.11
    0.6%
    376
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.12
    0.04
    311
    +0.11
    0.04
    335
    +0.10
    0.04
    Negative Logits
    ¸
    -3.56
    Ĭ
    -3.29
    ½
    -3.22
    Ģ
    -3.14
    ¬
    -3.07
    ŀ
    -3.01
    ĥ
    -3.00
    Ń
    -2.98
    §
    -2.96
    ¤
    -2.92
    POSITIVE LOGITS
    '));
    1.53
     harmless
    1.47
    ({
    1.43
    proj
    1.42
    olo
    1.40
    free
    1.39
     {
    1.39
    iest
    1.35
     agg
    1.35
     );
    1.31
    Activations Density 0.164%

    No Known Activations