© 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. 27220
    Prev
    Next
    INDEX
    Explanations

    elements that indicate lists or collections within a programming context

    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
    510
    +0.11
    0.6%
    334
    +0.11
    0.6%
    201
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.09
    17
    +0.11
    0.08
    271
    +0.10
    0.05
    Negative Logits
    )^[@
    -1.84
    ^[@
    -1.66
    enough
    -1.64
    $$\
    -1.56
     enough
    -1.55
     release
    -1.51
    helf
    -1.48
    heet
    -1.45
     yours
    -1.45
     Illustr
    -1.42
    POSITIVE LOGITS
    Ļª
    3.14
    ¿½
    2.89
    İ
    2.85
    Ģ
    2.71
    į
    2.63
    Īĺ
    2.54
    ĸ
    2.48
    ĩ
    2.40
    «
    2.31
    Ĩ
    2.24
    Activations Density 0.048%

    No Known Activations