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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27718
    Prev
    Next
    INDEX
    Explanations

    terms related to altruism and cooperative behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    376
    +0.14
    0.8%
    189
    +0.12
    0.7%
    415
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.14
    0.02
    415
    +0.12
    0.02
    302
    +0.11
    0.02
    Negative Logits
     forget
    -1.93
    wise
    -1.77
     minds
    -1.70
    assadors
    -1.66
    '?"
    -1.64
    obbsee
    -1.63
    ters
    -1.48
     notice
    -1.46
    orers
    -1.46
    )){
    -1.45
    POSITIVE LOGITS
    enstein
    1.99
    xton
    1.98
     cellar
    1.47
    ÅĽci
    1.47
     billing
    1.42
    ford
    1.42
    ppo
    1.41
    ende
    1.40
    pee
    1.39
    âĢŁ
    1.38
    Activations Density 0.018%

    No Known Activations