© 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. 29266
    Prev
    Next
    INDEX
    Explanations

    phrases indicating searching or discovery actions

    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
    376
    +0.18
    1.0%
    115
    +0.14
    0.8%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    25
    +0.18
    0.03
    314
    +0.14
    0.02
    148
    +0.13
    0.01
    Negative Logits
    ¦
    -3.06
    Ľ
    -2.95
    ĥ½
    -2.69
    ¬
    -2.55
    ī
    -2.53
    ½
    -2.48
    ĭ
    -2.46
    ¸
    -2.40
    Ŀ
    -2.39
    Ī
    -2.38
    POSITIVE LOGITS
    itives
    1.80
     guilty
    1.69
    ings
    1.63
     Aid
    1.60
    ably
    1.59
     someone
    1.58
    estine
    1.58
    ingly
    1.56
    atinib
    1.56
    ational
    1.49
    Activations Density 0.156%

    No Known Activations