© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26678
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and surgical procedures

    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
    203
    +0.21
    1.2%
    258
    +0.19
    1.1%
    271
    +0.17
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.21
    0.30
    271
    +0.19
    0.12
    17
    +0.17
    0.14
    Negative Logits
     boat
    -1.58
    experienced
    -1.54
     boards
    -1.51
    omet
    -1.47
     bracket
    -1.46
     tester
    -1.45
     craw
    -1.40
    otten
    -1.39
    ifying
    -1.38
    ixel
    -1.35
    POSITIVE LOGITS
    ĩ
    3.48
    ł
    3.34
    §
    3.24
    Ĩ
    3.16
    ĥ½
    3.16
    İ
    3.16
    ģ
    3.15
    ©
    3.14
    º
    3.13
    ĨĴ
    3.12
    Activations Density 1.424%

    No Known Activations