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

    Neuronpedia

    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. 2-MLP-SM
    11. 25737
    Prev
    Next
    INDEX
    Explanations

    terms related to uncertainty and insurance concepts

    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
    156
    +0.24
    1.4%
    448
    +0.12
    0.7%
    140
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    140
    +0.24
    0.06
    218
    +0.12
    0.07
    46
    +0.12
    0.06
    Negative Logits
    xico
    -1.95
    soever
    -1.79
     unable
    -1.56
     notified
    -1.53
     wondering
    -1.48
    rely
    -1.47
    indicated
    -1.46
    expected
    -1.46
     remain
    -1.46
    said
    -1.46
    POSITIVE LOGITS
    ¾
    1.90
    º
    1.78
    ±
    1.74
    ij
    1.69
    Ħ
    1.66
    İ
    1.66
     manners
    1.65
    ĸ
    1.65
    Ĵ
    1.63
    lan
    1.60
    Activations Density 2.537%

    No Known Activations