© 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. 28558
    Prev
    Next
    INDEX
    Explanations

    phrases that mention groups or quantities

    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
    343
    +0.12
    0.7%
    494
    +0.11
    0.6%
    477
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    249
    +0.12
    0.02
    335
    +0.11
    0.02
    477
    +0.10
    0.02
    Negative Logits
    Ĥ¬
    -2.52
    ŀ
    -2.42
    ¤
    -2.42
    Ĥ
    -2.37
    ¹
    -2.35
    Ł
    -2.34
    ĨĴ
    -2.33
    º
    -2.31
    Ļ
    -2.28
    Ń
    -2.24
    POSITIVE LOGITS
     dozen
    1.88
    ousand
    1.76
     hundred
    1.76
    ships
    1.71
    lie
    1.69
    ages
    1.66
    zet
    1.66
    tering
    1.65
    iece
    1.65
    frey
    1.64
    Activations Density 0.090%

    No Known Activations