© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 30058
    Prev
    Next
    INDEX
    Explanations

    references to numerical values and specific symbols

    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
    156
    +0.46
    3.1%
    111
    +0.44
    3.0%
    427
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.46
    0.04
    4
    +0.44
    0.04
    473
    +0.12
    0.04
    Negative Logits
    ħ
    -2.54
    <|outofrange|>
    -2.25
    ↵
    -2.25
    -2.25
    ↵
    -2.25
    <|outofrange|>
    -2.25
    <|outofrange|>
    -2.25
    ↵
    -2.25
    ↵
    -2.25
    ↵↵
    -2.25
    POSITIVE LOGITS
    ank
    1.45
    ookie
    1.43
    ERIAL
    1.41
    oultry
    1.40
     aeruginosa
    1.37
    ursuant
    1.35
    ensive
    1.35
    ediatric
    1.34
    INK
    1.33
    inte
    1.33
    Activations Density 0.023%

    No Known Activations