© 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. 27143
    Prev
    Next
    INDEX
    Explanations

    references to questionnaires and assessments

    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
    156
    +0.23
    1.3%
    365
    +0.14
    0.8%
    225
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.23
    0.16
    156
    +0.14
    0.09
    271
    +0.12
    0.07
    Negative Logits
     elegans
    -1.63
     coast
    -1.53
     radicals
    -1.53
     spirit
    -1.49
    abouts
    -1.49
     COPYRIGHT
    -1.48
     rogue
    -1.48
     queer
    -1.48
     moonlight
    -1.48
     exponential
    -1.48
    POSITIVE LOGITS
    nos
    1.77
    length
    1.65
    ĻĤ
    1.60
    indo
    1.47
    nam
    1.47
    matic
    1.46
    sync
    1.46
    true
    1.46
    illar
    1.45
    naire
    1.45
    Activations Density 0.388%

    No Known Activations