© 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 EvalsExportsinterp-engineNEWAPI 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. 25821
    Prev
    Next
    INDEX
    Explanations

    phrases indicating situational contexts or states

    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
    503
    +0.18
    1.1%
    274
    +0.15
    1.0%
    441
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.18
    0.02
    441
    +0.15
    0.01
    274
    +0.13
    0.01
    Negative Logits
    Ļª
    -1.78
     tranqu
    -1.71
     prayer
    -1.58
     pray
    -1.53
    bey
    -1.49
     falsely
    -1.48
     peaceful
    -1.47
    raj
    -1.46
    »¿
    -1.45
    ?_
    -1.44
    POSITIVE LOGITS
    ist
    2.21
    ists
    2.07
    ista
    1.99
    naire
    1.89
    ism
    1.75
    iste
    1.75
    ivated
    1.73
    table
    1.73
    iterator
    1.71
    emente
    1.69
    Activations Density 0.036%

    No Known Activations