© 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 EvalsExportsAPI 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. 25861
    Prev
    Next
    INDEX
    Explanations

    specific greetings or informal conversational openings

    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
    434
    +0.14
    0.8%
    393
    +0.14
    0.8%
    466
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.14
    0.45
    156
    +0.14
    0.24
    428
    +0.14
    0.36
    Negative Logits
    ĨĴ
    -3.22
    ĵ
    -3.05
    ¨
    -2.58
    Ī
    -2.54
    Īĺ
    -2.53
    ĥ
    -2.48
    ¯
    -2.45
    Ł
    -2.45
    Ĺ
    -2.44
    ı
    -2.43
    POSITIVE LOGITS
    oku
    1.76
    eting
    1.67
    enda
    1.64
     colleg
    1.61
     presses
    1.54
    endas
    1.49
     (“
    1.48
    ji
    1.47
    pton
    1.47
    agem
    1.45
    Activations Density 1.260%

    No Known Activations