© 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. 4-RES-SM
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds related to sodium and potassium

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    306
    +0.18
    1.0%
    369
    +0.13
    0.8%
    224
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.18
    0.01
    366
    +0.13
    0.01
    448
    +0.12
    0.01
    Negative Logits
    nament
    -2.05
    endants
    -1.77
    ockets
    -1.71
    eting
    -1.65
    thens
    -1.63
    ÃŃas
    -1.57
    hers
    -1.56
    EMENT
    -1.56
    ident
    -1.55
    undo
    -1.54
    POSITIVE LOGITS
    ħ
    3.29
    ·
    2.95
    ¯
    2.95
    «
    2.90
    ģ
    2.88
    §
    2.82
    ĻĤ
    2.76
    ī
    2.76
    ↵
    2.72
    ↵↵↵
    2.72
    Activations Density 0.045%

    No Known Activations