© 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 EvalsExportsAPI 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. 27335
    Prev
    Next
    INDEX
    Explanations

    variations of the expression of surprise or amazement

    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
    369
    +0.14
    0.8%
    111
    +0.12
    0.7%
    5
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.14
    0.02
    410
    +0.12
    0.02
    403
    +0.12
    0.01
    Negative Logits
    ĸ
    -1.69
    ³
    -1.48
    ructure
    -1.48
    atern
    -1.40
    opy
    -1.39
    aterally
    -1.39
    rceil
    -1.39
    Ĥ
    -1.38
     backdrop
    -1.37
    âĢĤ
    -1.36
    POSITIVE LOGITS
    ème
    2.00
     (@
    1.76
    rame
    1.70
    ammad
    1.68
    ydrates
    1.68
    lich
    1.67
    aron
    1.60
    onen
    1.60
    istory
    1.59
    ydrate
    1.58
    Activations Density 0.053%

    No Known Activations