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

    Neuronpedia

    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. 2-RES-SM
    11. 11178
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and their manipulation in programming

    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
    17
    +0.22
    1.3%
    47
    +0.14
    0.8%
    240
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.22
    0.02
    47
    +0.14
    0.09
    107
    +0.13
    0.04
    Negative Logits
    ĥ½
    -3.09
    º
    -2.96
    ¶
    -2.88
    ĺ
    -2.88
    ¦
    -2.87
    Ī
    -2.79
    Į
    -2.78
    ĨĴ
    -2.71
    ©
    -2.68
    ĸ
    -2.60
    POSITIVE LOGITS
     коÑĤоÑĢ
    1.62
     multid
    1.47
     varying
    1.45
     stacked
    1.41
     spaces
    1.39
     headed
    1.38
     torn
    1.35
     decir
    1.35
     possibly
    1.35
    =>
    1.33
    Activations Density 1.383%

    No Known Activations