© 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. 27457
    Prev
    Next
    INDEX
    Explanations

    references to the abbreviation "Fr," likely indicating a connection to individuals or titles

    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
    369
    +0.20
    1.1%
    28
    +0.13
    0.7%
    348
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    28
    +0.20
    0.02
    348
    +0.13
    0.02
    369
    +0.12
    0.01
    Negative Logits
    ¶
    -3.46
    ĥ
    -3.33
    ľ
    -3.31
    ¿½
    -3.28
    ¬
    -3.28
    ¥
    -3.22
    İ
    -3.10
    -3.07
    -3.07
           ↵
    -3.07
    POSITIVE LOGITS
    anks
    1.87
    idays
    1.69
    aced
    1.67
    iculously
    1.64
    amed
    1.57
    ames
    1.57
    ustration
    1.55
    isch
    1.53
    aces
    1.53
     visited
    1.51
    Activations Density 0.039%

    No Known Activations