© 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. 26295
    Prev
    Next
    INDEX
    Explanations

    references to negative effects or consequences

    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
    23
    +0.20
    1.1%
    474
    +0.11
    0.6%
    404
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.05
    325
    +0.11
    0.04
    156
    +0.11
    0.03
    Negative Logits
    eval
    -1.76
    sburg
    -1.72
    oit
    -1.70
    ists
    -1.57
    teenth
    -1.55
    module
    -1.53
    iece
    -1.52
    aced
    -1.51
    bibliography
    -1.50
    esque
    -1.50
    POSITIVE LOGITS
     hazard
    1.88
    hift
    1.80
     irritation
    1.78
    pan
    1.75
     delay
    1.71
     carcinogenesis
    1.68
     proportions
    1.66
     bleeding
    1.65
     accidents
    1.64
     distress
    1.64
    Activations Density 0.319%

    No Known Activations