© 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. 31126
    Prev
    Next
    INDEX
    Explanations

    numerical values and their combinations

    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
    203
    +0.12
    0.7%
    369
    +0.11
    0.6%
    307
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.12
    0.06
    125
    +0.11
    0.04
    203
    +0.11
    0.05
    Negative Logits
    ]]>
    -1.64
     selection
    -1.47
    =”
    -1.41
    .]{}
    -1.41
     alike
    -1.35
    entes
    -1.35
     mess
    -1.35
     organizing
    -1.32
    &#
    -1.32
    matic
    -1.30
    POSITIVE LOGITS
    »¿
    2.95
    Ĥ
    2.85
    ·
    2.79
    ³
    2.72
    ĥ½
    2.69
    ¶
    2.67
    Ĵ
    2.57
    ¹
    2.49
    ²
    2.49
    ®
    2.43
    Activations Density 0.296%

    No Known Activations