© 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. 1-RES-SM
    11. 24454
    Prev
    Next
    INDEX
    Explanations

    references to software extensions

    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
    156
    +0.14
    0.8%
    376
    +0.14
    0.8%
    434
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.14
    0.02
    473
    +0.14
    0.01
    217
    +0.12
    0.02
    Negative Logits
    Ĥ¬
    -1.88
    ubicin
    -1.83
    other
    -1.75
    others
    -1.70
    psy
    -1.63
    hav
    -1.60
    vez
    -1.56
    iente
    -1.55
    woke
    -1.53
    rift
    -1.51
    POSITIVE LOGITS
    ized
    1.87
     invariance
    1.79
     [-
    1.70
     slots
    1.69
    ally
    1.61
    arily
    1.58
    ivity
    1.57
     brackets
    1.57
    ised
    1.49
     radius
    1.49
    Activations Density 0.098%

    No Known Activations