© 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. 1-RES-SM
    11. 28130
    Prev
    Next
    INDEX
    Explanations

    mentions of polls and polling-related concepts

    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
    221
    +0.14
    0.8%
    125
    +0.12
    0.7%
    392
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.14
    0.02
    221
    +0.12
    0.02
    113
    +0.11
    0.01
    Negative Logits
    ľĵ
    -3.03
    ķ
    -2.96
    ĸ´
    -2.80
    ĭ
    -2.75
    ĸ
    -2.74
    ĵ
    -2.74
    Ŀ
    -2.64
    Ĭ
    -2.59
    ©
    -2.59
    ľ
    -2.58
    POSITIVE LOGITS
    uted
    2.56
    ute
    2.53
    utive
    2.13
    uting
    2.10
    ution
    2.01
    utable
    1.96
    istar
    1.96
    uter
    1.96
    inson
    1.90
    ination
    1.85
    Activations Density 0.102%

    No Known Activations