© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27247
    Prev
    Next
    INDEX
    Explanations

    expressions related to the methodology and presentation of research findings

    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
    198
    +0.16
    0.9%
    448
    +0.13
    0.7%
    12
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.16
    0.13
    478
    +0.13
    -0.02
    198
    +0.12
    0.02
    Negative Logits
    rency
    -1.71
    iac
    -1.70
    pective
    -1.69
    illion
    -1.63
     etc
    -1.59
    ry
    -1.55
    #,
    -1.53
    Hz
    -1.52
     themselves
    -1.50
     Paint
    -1.50
    POSITIVE LOGITS
    ±
    2.94
    ĨĴ
    2.85
    ĻĤ
    2.80
    ı
    2.77
    ķ
    2.76
    §
    2.70
    Į
    2.68
    ²
    2.62
    ĸ´
    2.51
    ĩ
    2.50
    Activations Density 2.235%

    No Known Activations