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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26210
    Prev
    Next
    INDEX
    Explanations

    instances of emotional conflict and significant life experiences

    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/2-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.2.hook_mlp_out
    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
    439
    +0.13
    0.7%
    376
    +0.12
    0.7%
    176
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.13
    0.13
    264
    +0.12
    0.14
    363
    +0.11
    0.12
    Negative Logits
    ¦
    -2.30
    ł
    -1.98
    Īĺ
    -1.97
    ³
    -1.95
    ¿½
    -1.92
     brow
    -1.78
    ĥ½
    -1.70
    ´
    -1.70
    ķ
    -1.64
    ľ
    -1.58
    POSITIVE LOGITS
    ág
    2.29
    ÃŃf
    1.85
    aria
    1.79
    éd
    1.72
     lately
    1.66
     comprises
    1.64
    bibr
    1.61
    / 
    1.60
    orf
    1.59
    arcin
    1.57
    Activations Density 0.899%

    No Known Activations