© 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. 28619
    Prev
    Next
    INDEX
    Explanations

    references to licenses

    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
    369
    +0.19
    1.1%
    357
    +0.15
    0.9%
    291
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    357
    +0.19
    0.02
    291
    +0.15
    0.04
    10
    +0.13
    0.03
    Negative Logits
    nos
    -1.67
    ```
    -1.64
    istan
    -1.52
    ulos
    -1.46
    tery
    -1.46
    holder
    -1.43
    vous
    -1.42
    ocha
    -1.41
    rais
    -1.38
    conviction
    -1.37
    POSITIVE LOGITS
    ĥ½
    2.31
    ij
    1.91
    ĨĴ
    1.90
    ĸ
    1.82
    Ĵ
    1.82
    1.80
    1.80
    1.80
    ↵↵
    1.80
    ↵
    1.80
    Activations Density 0.269%

    No Known Activations