© 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. 2-RES-SM
    11. 9902
    Prev
    Next
    INDEX
    Explanations

    topics related to social structures and community interactions

    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
    344
    +0.14
    0.8%
    302
    +0.12
    0.7%
    161
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.14
    0.15
    143
    +0.12
    0.08
    241
    +0.11
    0.11
    Negative Logits
    <|outofrange|>
    -6.53
    -6.53
    ↵
    -6.53
    ↵
    -6.53
    <|outofrange|>
    -6.53
    ↵  âĢĥ
    -6.53
    č↵
    -6.53
    -6.53
    -6.53
    ↵
    -6.53
    POSITIVE LOGITS
     alike
    2.83
     respectively
    2.67
     are
    1.76
     deserve
    1.74
     herein
    1.67
     tolerated
    1.57
     thereof
    1.55
     required
    1.55
     involved
    1.52
     contributed
    1.47
    Activations Density 1.883%

    No Known Activations