© 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. 27758
    Prev
    Next
    INDEX
    Explanations

    expressions of enjoyment or positive 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/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
    160
    +0.15
    0.8%
    43
    +0.12
    0.6%
    66
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    231
    +0.15
    0.01
    119
    +0.12
    0.01
    27
    +0.11
    0.01
    Negative Logits
    ĥ½
    -5.03
    Īĺ
    -4.84
    ·¸
    -4.83
    ī
    -4.79
    ©
    -4.73
    »
    -4.67
    ®
    -4.62
    ¬
    -4.58
    ½
    -4.51
    µ
    -4.51
    POSITIVE LOGITS
     technology
    1.68
     characterization
    1.61
     placement
    1.50
     parent
    1.46
     activity
    1.42
     prior
    1.38
     ("
    1.37
     technologies
    1.37
     choice
    1.37
     techniques
    1.37
    Activations Density 0.002%

    No Known Activations