© 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. 13785
    Prev
    Next
    INDEX
    Explanations

    references to numerical counts and categories

    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
    156
    +0.16
    0.9%
    419
    +0.15
    0.9%
    121
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.16
    0.06
    26
    +0.15
    0.04
    121
    +0.12
    0.05
    Negative Logits
    Ķ
    -2.07
    ĥ½
    -2.01
    ¦
    -2.01
    µ
    -1.90
    Īĺ
    -1.85
    ©
    -1.82
    ¨
    -1.78
    ª
    -1.76
    ĺ
    -1.74
    ľ
    -1.71
    POSITIVE LOGITS
     punches
    1.68
     punch
    1.57
     rounds
    1.54
     halves
    1.51
     sides
    1.49
     coin
    1.46
     heads
    1.46
     consecutive
    1.44
     arrangements
    1.43
     cups
    1.40
    Activations Density 0.751%

    No Known Activations