© 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. 2-RES-SM
    11. 11147
    Prev
    Next
    INDEX
    Explanations

    references to time and scheduling details

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    161
    +0.16
    0.9%
    422
    +0.15
    0.9%
    321
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.16
    0.09
    161
    +0.15
    0.05
    421
    +0.14
    0.04
    Negative Logits
     nil
    -1.80
    ains
    -1.51
    ain
    -1.47
    hee
    -1.44
    aturation
    -1.38
     )"
    -1.33
     normalization
    -1.33
    agn
    -1.32
    msgstr
    -1.30
    tone
    -1.30
    POSITIVE LOGITS
    Ļ
    2.78
    ¿½
    2.76
    ³
    2.75
    Ĺ
    2.54
    IJ
    2.53
    ª
    2.37
    Ĩ
    2.35
    ij
    2.35
    ¿
    2.34
    »
    2.31
    Activations Density 4.184%

    No Known Activations