© 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. 27313
    Prev
    Next
    INDEX
    Explanations

    terms related to medical or scientific classifications and methodologies

    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
    111
    +0.15
    0.8%
    376
    +0.14
    0.8%
    389
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.01
    389
    +0.14
    0.01
    338
    +0.13
    0.01
    Negative Logits
    lessly
    -1.97
     completion
    -1.80
     elusive
    -1.55
     endless
    -1.51
     COPYRIGHT
    -1.48
     gradual
    -1.44
     maintaining
    -1.44
     exact
    -1.43
     numerous
    -1.42
     violations
    -1.38
    POSITIVE LOGITS
    Ĵ
    3.30
    ĻĤ
    3.16
    Īĺ
    3.15
    ¢
    3.10
    ķ
    2.99
    ĸ
    2.93
    ¿½
    2.75
    ł
    2.69
    Ĭ
    2.66
    Ī
    2.66
    Activations Density 0.037%

    No Known Activations