© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27306
    Prev
    Next
    INDEX
    Explanations

    references to transformation or physical change, particularly in the context of creative or technical processes

    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
    386
    +0.13
    0.8%
    46
    +0.12
    0.7%
    5
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.13
    0.01
    386
    +0.12
    0.01
    196
    +0.11
    0.01
    Negative Logits
    unnumbered
    -2.07
    ked
    -1.66
    qq
    -1.57
     knowing
    -1.49
     same
    -1.48
    undry
    -1.47
     endless
    -1.46
     months
    -1.46
     hours
    -1.44
     Promise
    -1.44
    POSITIVE LOGITS
    lets
    1.86
    ettes
    1.81
    oon
    1.77
    engers
    1.76
    itious
    1.74
    iens
    1.72
    ician
    1.70
    icians
    1.70
    lic
    1.70
    antine
    1.70
    Activations Density 0.037%

    No Known Activations