© 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. 26637
    Prev
    Next
    INDEX
    Explanations

    references to history

    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
    365
    +0.15
    0.9%
    166
    +0.15
    0.8%
    460
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.15
    0.01
    111
    +0.15
    0.03
    365
    +0.14
    0.02
    Negative Logits
    §
    -2.88
    Ħ
    -2.82
    į
    -2.74
    Ĭ
    -2.70
    ·¸
    -2.68
    µ
    -2.58
    ľĵ
    -2.58
    ¯
    -2.57
    ĥ½
    -2.48
    ħ
    -2.48
    POSITIVE LOGITS
    ontal
    1.89
    ocene
    1.75
    ieval
    1.59
    aday
    1.51
     reconstruction
    1.50
     Interests
    1.48
    fare
    1.48
     dysplasia
    1.45
    ylvania
    1.45
    telling
    1.44
    Activations Density 0.147%

    No Known Activations