© 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. 12585
    Prev
    Next
    INDEX
    Explanations

    specific alphanumeric codes or identifiers related to variables and measurements

    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
    111
    +0.64
    5.9%
    156
    +0.56
    5.2%
    20
    +0.06
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.64
    0.01
    67
    +0.56
    0.01
    37
    +0.06
    0.01
    Negative Logits
    <|outofrange|>
    -2.32
     ↵
    -2.32
    ↵
    -2.32
    <|outofrange|>
    -2.32
    <|outofrange|>
    -2.32
    ↵
    -2.32
    ↵
    -2.32
    <|outofrange|>
    -2.32
    <|outofrange|>
    -2.32
     ↵
    -2.32
    POSITIVE LOGITS
    elly
    1.25
    tico
    1.18
    tica
    1.14
    iang
    1.13
    dess
    1.05
    unov
    1.03
    ERTY
    1.03
    STM
    1.03
    coat
    1.00
    ikes
    1.00
    Activations Density 0.028%

    No Known Activations