© 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. 2-RES-SM
    11. 32117
    Prev
    Next
    INDEX
    Explanations

    references to names 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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    472
    +0.13
    0.7%
    269
    +0.12
    0.7%
    91
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.13
    0.04
    162
    +0.12
    0.04
    51
    +0.12
    0.03
    Negative Logits
    ricular
    -1.93
    ared
    -1.64
    oration
    -1.59
    aration
    -1.50
    ores
    -1.49
     writer
    -1.49
    riction
    -1.47
    oring
    -1.44
    dern
    -1.42
    CTION
    -1.42
    POSITIVE LOGITS
    Īĺ
    1.85
    Ļª
    1.65
    '$,
    1.52
     away
    1.52
     alone
    1.50
    £
    1.47
    Ĭ
    1.47
    lish
    1.46
    eligible
    1.44
    ¿
    1.43
    Activations Density 0.087%

    No Known Activations