© 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. 28612
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to uncertainty and inquiry

    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
    19
    +0.13
    0.7%
    239
    +0.12
    0.7%
    3
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    356
    +0.13
    0.05
    505
    +0.12
    0.05
    208
    +0.12
    0.07
    Negative Logits
    ¯
    -2.42
    Ħ
    -2.41
    °
    -2.40
    ¬
    -2.27
    ®
    -2.17
    ¼
    -2.16
    §
    -2.16
    Ĥ
    -2.14
    ¹
    -2.13
    Į
    -2.13
    POSITIVE LOGITS
     hurt
    1.98
     harm
    1.90
    ships
    1.59
    wed
    1.59
     there
    1.58
     duty
    1.56
    aths
    1.55
     bodily
    1.54
     stolen
    1.53
     immense
    1.49
    Activations Density 1.019%

    No Known Activations