© 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. 29486
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "danger."

    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
    410
    +0.20
    1.1%
    111
    +0.12
    0.6%
    113
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.20
    0.01
    111
    +0.12
    0.01
    42
    +0.11
    0.01
    Negative Logits
    illance
    -1.66
    oclonal
    -1.48
    heimer
    -1.44
     et
    -1.42
    arch
    -1.42
    schemas
    -1.41
    mente
    -1.37
    velopment
    -1.36
     mellitus
    -1.31
    lam
    -1.29
    POSITIVE LOGITS
    ŀ
    1.77
    ¥
    1.74
     rush
    1.65
    Ļ
    1.64
    ²
    1.59
    ĥ
    1.58
    ¡
    1.53
    rade
    1.52
    ½
    1.52
    £
    1.51
    Activations Density 0.016%

    No Known Activations