© 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. 1-RES-SM
    11. 27953
    Prev
    Next
    INDEX
    Explanations

    references to data-related concepts or terms

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    372
    +0.13
    0.7%
    148
    +0.13
    0.7%
    250
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.13
    0.02
    250
    +0.13
    0.02
    361
    +0.12
    0.01
    Negative Logits
     choice
    -1.85
     mocking
    -1.60
    >$
    -1.58
    soever
    -1.52
     LIABILITY
    -1.52
    visibility
    -1.48
     choices
    -1.48
     tuned
    -1.45
     override
    -1.45
     false
    -1.44
    POSITIVE LOGITS
    ¿½
    2.91
    º
    2.80
    ©
    2.77
    »
    2.77
    ²
    2.73
    «
    2.70
    ģ
    2.68
    ½
    2.66
    Ģ
    2.56
    ķ
    2.54
    Activations Density 0.091%

    No Known Activations