© 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 EvalsExportsinterp-engineNEWAPI 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. 25390
    Prev
    Next
    INDEX
    Explanations

    references to data metrics and statistics related to posts and links

    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
    23
    +0.23
    1.4%
    332
    +0.14
    0.8%
    7
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.23
    0.05
    7
    +0.14
    0.09
    222
    +0.14
    0.09
    Negative Logits
    boat
    -1.81
    rah
    -1.68
     shooter
    -1.67
    ville
    -1.67
    ibo
    -1.57
    boats
    -1.57
    runner
    -1.55
    ungen
    -1.54
    assic
    -1.53
    wall
    -1.53
    POSITIVE LOGITS
     evenly
    1.66
    operatively
    1.65
    ?'
    1.64
    *"
    1.55
    matically
    1.51
    ...?"
    1.47
    atively
    1.43
    "?"
    1.42
     "</
    1.40
    ferentially
    1.39
    Activations Density 4.466%

    No Known Activations