© 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. 30220
    Prev
    Next
    INDEX
    Explanations

    references to facilities or infrastructure

    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
    386
    +0.17
    1.0%
    194
    +0.15
    0.9%
    203
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.17
    0.04
    338
    +0.15
    0.03
    74
    +0.13
    0.04
    Negative Logits
    arrows
    -1.73
     slightest
    -1.69
     hardest
    -1.65
     defeated
    -1.62
     wounded
    -1.60
    sson
    -1.58
     word
    -1.53
     deceased
    -1.51
     sentence
    -1.51
     sentences
    -1.51
    POSITIVE LOGITS
    ³
    2.94
    Ĭ
    2.68
    ª
    2.50
    ¤
    2.42
    IJ
    2.40
    ĵ
    2.37
    ķ
    2.36
    µ
    2.31
    İ
    2.27
    Ĥ
    2.27
    Activations Density 1.058%

    No Known Activations