Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 12132
    Prev
    Next
    INDEX
    Explanations

    phrases related to license agreements and legal disclaimers

    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
    290
    +0.13
    0.7%
    450
    +0.12
    0.6%
    34
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.13
    0.04
    450
    +0.12
    0.04
    273
    +0.10
    0.04
    Negative Logits
    separator
    -1.52
    .[]{
    -1.50
    ).](
    -1.46
    []{
    -1.43
    ición
    -1.42
     therein
    -1.42
    .’”
    -1.41
    oretic
    -1.38
    icals
    -1.37
    ?’
    -1.37
    POSITIVE LOGITS
    //
    1.75
     unanimously
    1.54
    veis
    1.52
    //----------------------------------------------------------------
    1.51
    #
    1.49
    ///
    1.43
    ////////////////////////////////////////////////////////////////
    1.37
    ––––––––
    1.36
    ////////////////
    1.34
     //
    1.32
    Activations Density 0.236%

    No Known Activations