© 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 EvalsExportsinterp-engineNEWAPI 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. 26670
    Prev
    Next
    INDEX
    Explanations

    instances of sharing and collaboration in various contexts

    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
    293
    +0.14
    0.8%
    400
    +0.13
    0.7%
    17
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    170
    +0.14
    0.08
    293
    +0.13
    0.08
    246
    +0.13
    0.09
    Negative Logits
    inally
    -1.71
     farmers
    -1.64
     worse
    -1.59
    iners
    -1.48
     better
    -1.46
     infantry
    -1.43
    asty
    -1.40
     cyclists
    -1.40
     gentlemen
    -1.40
     peasants
    -1.38
    POSITIVE LOGITS
    orship
    1.83
    isma
    1.62
    ductory
    1.45
    endas
    1.43
    /{
    1.43
     previously
    1.42
    /-/
    1.40
     shares
    1.40
     voc
    1.39
    MENTS
    1.39
    Activations Density 1.753%

    No Known Activations