© 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. 29136
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics regarding events or figures in various contexts

    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
    +0.14
    0.8%
    276
    +0.14
    0.8%
    457
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.14
    0.10
    307
    +0.14
    0.11
    477
    +0.13
    0.12
    Negative Logits
     hazard
    -1.81
     destiny
    -1.62
     fame
    -1.62
     conjecture
    -1.60
     responsibility
    -1.57
     burden
    -1.56
    ribution
    -1.49
     causation
    -1.47
    nement
    -1.43
     domination
    -1.42
    POSITIVE LOGITS
    ĥ½
    2.38
    ¶
    2.11
    ³
    2.08
    ¾
    2.06
    ª
    1.99
    th
    1.98
    ·
    1.92
    ¬
    1.87
    ↵
    1.86
    ↵
    1.86
    Activations Density 0.352%

    No Known Activations