© 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 EvalsExportsAPI 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. 28339
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and compounds relevant to scientific research

    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
    261
    +0.13
    0.7%
    497
    +0.12
    0.7%
    77
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    77
    +0.13
    0.03
    275
    +0.12
    0.03
    18
    +0.12
    0.06
    Negative Logits
    (@"
    -1.50
     lately
    -1.46
    qa
    -1.43
     entit
    -1.42
     qualifying
    -1.40
    ↵
    -1.38
    ![
    -1.37
    versation
    -1.35
    owing
    -1.35
     ahead
    -1.35
    POSITIVE LOGITS
    ³
    3.84
    ľ
    3.83
    Ń
    3.81
    ·¸
    3.79
    »¿
    3.79
    ħ
    3.79
    ¿
    3.78
    »
    3.77
    ±
    3.73
    ¹
    3.68
    Activations Density 1.023%

    No Known Activations