© 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. 1-RES-SM
    11. 24618
    Prev
    Next
    INDEX
    Explanations

    specific structural components and syntax in programming or configuration languages

    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
    23
    +0.14
    0.8%
    332
    +0.13
    0.7%
    184
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    0
    +0.14
    0.07
    136
    +0.13
    -0.04
    197
    +0.12
    0.04
    Negative Logits
    č↵
    -3.00
    <|outofrange|>
    -3.00
    ↵
    -3.00
    ↵
    -3.00
     ↵
    -3.00
    -3.00
    -3.00
    č↵
    -3.00
    -3.00
    ↵  Âł
    -3.00
    POSITIVE LOGITS
    >\
    1.59
    chel
    1.58
    {}{
    1.58
     Minor
    1.43
    }|^
    1.42
    >
    1.42
    }"
    1.41
    >();
    1.40
    including
    1.40
    >(
    1.39
    Activations Density 1.647%

    No Known Activations