© 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. MLP Post
    9. 0-MLP-SM
    11. 28866
    Prev
    Next
    INDEX
    Explanations

    references to Tuscany and related geographical or cultural terms

    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
    111
    +0.17
    1.0%
    180
    +0.12
    0.7%
    330
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.17
    0.01
    180
    +0.12
    0.01
    468
    +0.11
    0.01
    Negative Logits
    č↵
    -1.97
    ↵
    -1.74
    hip
    -1.68
     âĻª"
    -1.58
    '?"
    -1.57
     matter
    -1.55
    ching
    -1.52
     '</
    -1.52
    tering
    -1.43
     sure
    -1.41
    POSITIVE LOGITS
    erad
    1.65
    "}](#
    1.64
    nor
    1.61
    ols
    1.56
    enos
    1.52
    eno
    1.51
    enario
    1.50
    eto
    1.47
    olta
    1.46
    enstein
    1.45
    Activations Density 0.012%

    No Known Activations