© 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. 12655
    Prev
    Next
    INDEX
    Explanations

    biological terms related to cellular and extracellular components

    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
    +0.17
    1.0%
    148
    +0.15
    0.9%
    467
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    148
    +0.17
    0.01
    343
    +0.15
    0.01
    448
    +0.12
    0.01
    Negative Logits
    opard
    -2.26
    unting
    -1.77
    ouses
    -1.76
    heets
    -1.68
    rile
    -1.65
    heet
    -1.61
    unts
    -1.59
    apest
    -1.58
    že
    -1.57
    wegian
    -1.56
    POSITIVE LOGITS
    £
    2.88
    ŀ
    2.72
    ·¸
    2.69
    Ł
    2.66
    ij
    2.60
    º
    2.59
    Ģ
    2.59
    ķ
    2.58
    ł
    2.50
    ·
    2.46
    Activations Density 0.052%

    No Known Activations