© 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. 13020
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to create" or its derivatives

    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
    144
    +0.16
    0.9%
    74
    +0.13
    0.7%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    252
    +0.16
    0.03
    144
    +0.13
    0.02
    416
    +0.12
    0.02
    Negative Logits
    ij
    -2.61
    ĻĤ
    -2.48
    ©
    -2.24
    ĥ½
    -2.12
    Ĭ
    -2.10
    ª
    -2.04
    ±
    -2.00
    ĵ
    -1.92
    Ĥ¬
    -1.89
    ¾
    -1.86
    POSITIVE LOGITS
    chol
    2.30
    ctomy
    2.17
    ction
    1.89
     reductase
    1.88
    ctions
    1.87
    chin
    1.80
    iling
    1.73
    cted
    1.73
     Springs
    1.70
    fficients
    1.70
    Activations Density 0.257%

    No Known Activations