© 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. 10517
    Prev
    Next
    INDEX
    Explanations

    expressions of uncertainty and questioning in communication

    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
    444
    +0.14
    0.8%
    369
    +0.14
    0.8%
    323
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.14
    0.02
    323
    +0.14
    0.05
    431
    +0.13
    0.06
    Negative Logits
    ylon
    -1.67
    thems
    -1.53
    googleapis
    -1.50
    arynge
    -1.44
    asts
    -1.43
    fecture
    -1.41
    ongs
    -1.40
    ]"
    -1.40
    ently
    -1.36
    itatively
    -1.31
    POSITIVE LOGITS
     BGCOLOR
    1.53
    ctomy
    1.49
     shown
    1.46
    \_
    1.32
    guard
    1.30
    guards
    1.30
    ()->
    1.27
    :**
    1.27
    >/
    1.26
     told
    1.25
    Activations Density 5.136%

    No Known Activations