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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11269
    Prev
    Next
    INDEX
    Explanations

    import statements in programming code

    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
    396
    +0.14
    0.8%
    478
    +0.13
    0.7%
    427
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    396
    +0.14
    0.15
    325
    +0.13
    0.12
    399
    +0.11
    0.04
    Negative Logits
    cule
    -1.81
    enter
    -1.79
    ![**
    -1.70
    :`
    -1.63
    astro
    -1.52
    ``
    -1.50
    AFFIRMED
    -1.46
    orphic
    -1.45
    tbody
    -1.44
    same
    -1.43
    POSITIVE LOGITS
    ¼
    2.10
     Kit
    1.76
    ij
    1.61
    cht
    1.60
    wered
    1.59
     Manual
    1.47
                ↵
    1.46
    č↵
    1.46
    ↵↵
    1.46
    č↵
    1.46
    Activations Density 3.767%

    No Known Activations