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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 29314
    Prev
    Next
    INDEX
    Explanations

    significant achievements and milestones in personal or shared experiences

    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
    198
    +0.17
    1.0%
    186
    +0.16
    0.9%
    50
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.17
    0.10
    389
    +0.16
    0.13
    80
    +0.13
    0.09
    Negative Logits
    banks
    -1.62
    ahoma
    -1.59
    ubicin
    -1.57
    soever
    -1.57
    uties
    -1.52
    erce
    -1.47
    ictionaries
    -1.47
    aurus
    -1.46
    culation
    -1.46
    NULL
    -1.45
    POSITIVE LOGITS
     fixture
    1.77
     bracket
    1.50
     mould
    1.47
     vista
    1.46
     stage
    1.40
    point
    1.40
     homogen
    1.39
     quantity
    1.37
     metal
    1.34
     landmark
    1.32
    Activations Density 1.472%

    No Known Activations