© 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. 29580
    Prev
    Next
    INDEX
    Explanations

    expressions of excitement or enthusiasm

    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
    478
    +0.19
    1.1%
    115
    +0.11
    0.6%
    23
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    377
    +0.19
    0.03
    185
    +0.11
    0.03
    507
    +0.11
    0.03
    Negative Logits
    fficients
    -2.05
    essee
    -1.98
    ostat
    -1.75
    etric
    -1.70
    osti
    -1.69
    80211
    -1.67
     notation
    -1.65
    phrine
    -1.61
    esium
    -1.59
    ensity
    -1.59
    POSITIVE LOGITS
    ¼
    2.45
    ¸
    2.33
    ½
    2.29
    Ĵ
    2.24
    ı
    2.23
    ¤
    2.16
    ±
    1.96
     Continue
    1.89
    Ĺ
    1.86
    °
    1.84
    Activations Density 0.104%

    No Known Activations