© 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. 2-RES-SM
    11. 30424
    Prev
    Next
    INDEX
    Explanations

    text related to prerequisites or prior conditions

    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
    46
    +0.14
    0.8%
    498
    +0.12
    0.7%
    164
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    46
    +0.14
    0.02
    498
    +0.12
    0.02
    164
    +0.12
    0.02
    Negative Logits
    Ĵ
    -3.49
    Ļª
    -3.43
    ĸ´
    -3.21
    °
    -3.06
    ¥
    -3.01
    Į
    -2.98
    £
    -2.89
    Ļ
    -2.88
    ľĵ
    -2.86
    ¡
    -2.84
    POSITIVE LOGITS
    paring
    1.78
    ppers
    1.76
    fecture
    1.71
    valence
    1.68
    paration
    1.68
    requ
    1.61
     entry
    1.61
    ference
    1.61
    iser
    1.57
    pper
    1.55
    Activations Density 0.083%

    No Known Activations