© 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. 0-MLP-SM
    11. 26965
    Prev
    Next
    INDEX
    Explanations

    terms related to provocation or instigation

    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
    470
    +0.13
    0.7%
    410
    +0.13
    0.7%
    241
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    415
    +0.13
    0.01
    486
    +0.13
    0.01
    326
    +0.12
    0.01
    Negative Logits
    hip
    -1.96
    >()
    -1.62
    shore
    -1.60
    )$)
    -1.54
    ktop
    -1.50
    Ļª
    -1.48
    ward
    -1.45
    vere
    -1.41
    ever
    -1.39
    ME
    -1.38
    POSITIVE LOGITS
    iant
    1.40
    orov
    1.39
    nor
    1.38
     matches
    1.38
    itals
    1.37
    aceous
    1.36
    ainties
    1.36
    idently
    1.34
     spots
    1.33
     deton
    1.33
    Activations Density 3.222%

    No Known Activations