© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10215
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their attributes

    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
    481
    +0.13
    0.7%
    174
    +0.11
    0.6%
    372
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.13
    0.04
    155
    +0.11
    0.05
    397
    +0.10
    0.04
    Negative Logits
    abad
    -2.14
     alike
    -1.67
    istan
    -1.54
     successfully
    -1.51
    ="{
    -1.50
     recognize
    -1.43
    ceeded
    -1.38
    ?
    -1.37
    noreply
    -1.36
    =".
    -1.35
    POSITIVE LOGITS
    lest
    1.76
    Ļ
    1.62
    liest
    1.58
    ↵
    1.54
    1.54
    1.54
    ↵
    1.54
    ↵
    1.54
    ↵↵↵
    1.54
    ↵
    1.54
    Activations Density 0.542%

    No Known Activations