© 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. 27312
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to posts and interactions

    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
    84
    +0.11
    0.6%
    40
    +0.11
    0.6%
    261
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.11
    0.03
    69
    +0.11
    0.03
    167
    +0.11
    0.02
    Negative Logits
     '
    -1.56
     subtypes
    -1.49
     supply
    -1.44
    ''
    -1.43
    .");
    -1.42
     term
    -1.40
     generation
    -1.40
    ¿½
    -1.37
    obar
    -1.32
    arton
    -1.32
    POSITIVE LOGITS
    tah
    1.70
    noreply
    1.69
    essions
    1.68
    rowser
    1.58
    catalina
    1.56
    oddsidemargin
    1.55
    izer
    1.52
    idone
    1.52
    poons
    1.48
    cloth
    1.46
    Activations Density 0.129%

    No Known Activations