© 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. 27638
    Prev
    Next
    INDEX
    Explanations

    instances of the word "immediately."

    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
    376
    +0.11
    0.6%
    497
    +0.11
    0.6%
    69
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.11
    0.02
    33
    +0.11
    0.02
    404
    +0.10
    0.02
    Negative Logits
    Į
    -3.85
    ŀ
    -3.58
    Ĵ
    -3.48
    Ķ
    -3.46
    ľĵ
    -3.33
    ĵ
    -3.32
    Ľ
    -3.28
    ĭ
    -3.27
    Ĩ
    -3.27
    ¾
    -3.26
    POSITIVE LOGITS
     identifiable
    1.56
     recognizable
    1.56
     thereafter
    1.48
     supra
    1.45
     ?>
    1.42
     '')
    1.41
     ejected
    1.40
    iston
    1.39
     ERROR
    1.38
     transported
    1.38
    Activations Density 0.062%

    No Known Activations