© 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. 29675
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "breaking" in various contexts

    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
    164
    +0.15
    0.8%
    180
    +0.13
    0.7%
    22
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.15
    0.03
    403
    +0.13
    0.03
    4
    +0.11
    0.03
    Negative Logits
    awning
    -1.61
     owning
    -1.52
     having
    -1.51
    uka
    -1.40
    iente
    -1.39
    atinib
    -1.37
    HDL
    -1.36
     managing
    -1.35
    ours
    -1.34
    ubicin
    -1.31
    POSITIVE LOGITS
     question
    1.75
    hearted
    1.69
     questions
    1.68
    point
    1.67
    points
    1.67
    asted
    1.66
    dorff
    1.61
    Ģ
    1.56
     point
    1.56
     forth
    1.51
    Activations Density 5.434%

    No Known Activations