© 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. 12399
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, specifically Manchester United, and other football-related terms

    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
    271
    +0.16
    0.9%
    111
    +0.12
    0.7%
    182
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.16
    0.01
    34
    +0.12
    0.11
    202
    +0.11
    0.07
    Negative Logits
    ¯
    -3.19
    ±
    -2.85
    ļ
    -2.64
    <|outofrange|>
    -2.58
    ↵↵
    -2.58
    ↵
    -2.58
    <|outofrange|>
    -2.58
    č↵
    -2.58
           ↵
    -2.58
    ↵↵
    -2.58
    POSITIVE LOGITS
    udeau
    1.76
    gow
    1.68
     (@
    1.66
    acker
    1.65
    igator
    1.64
     Stadium
    1.57
    à±ģ
    1.56
    sson
    1.51
    ISPR
    1.51
    ãĤ£
    1.49
    Activations Density 1.205%

    No Known Activations