© 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. 2-RES-SM
    11. 26919
    Prev
    Next
    INDEX
    Explanations

    programming language names and related terms

    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
    +0.43
    2.6%
    111
    +0.19
    1.2%
    235
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    48
    +0.43
    0.05
    298
    +0.19
    0.04
    156
    +0.12
    0.04
    Negative Logits
    ĥ½
    -2.63
    ĭ
    -2.45
    Ĭ
    -2.39
                ↵
    -2.23
    <|outofrange|>
    -2.23
           ↵
    -2.23
    -2.23
    -2.23
    <|outofrange|>
    -2.23
    -2.23
    POSITIVE LOGITS
    INGTON
    1.47
    ING
    1.40
    lining
    1.34
    itness
    1.32
    pton
    1.31
    OID
    1.29
    keit
    1.27
     way
    1.25
     relies
    1.24
    terday
    1.24
    Activations Density 0.168%

    No Known Activations